LLM API Providers Leaderboard - Comparison of over 500 AI Model endpoints
Comparison of API provider performance across over 500 AI Model endpoints, including from OpenAI, Google, DeepSeek and others, across key performance metrics including price, time per task, latency, context window and more.
For more details including relating to our methodology, see our FAQs.
Further Analysis | |||||||||
|---|---|---|---|---|---|---|---|---|---|
Gemini 4 Carbon (high) | 60 | $7.76 | 30.7 | 68.04 | 12.8% | 1M | Proprietary | ||
Claude Opus 5.5 (max) | 59 | $10.04 | 26.7 | 369.68 | 7.9% | 1M | Proprietary | ||
Claude Opus 5.5 (max) | 59 | $10.04 | 25.4 | 365.20 | 5.3% | 1M | Proprietary | ||
Claude Opus 5.5 (max) | 59 | $21.07 | 24.8 | 366.88 | 3.3% | 1M | Proprietary | ||
Claude Opus 5.5 (max) | 59 | $11.43 | 30.1 | 296.83 | 8.9% | 1M | Proprietary | ||
Gemini 4 Carbon (medium) | 58 | $6.59 | 24.5 | 29.42 | 7.6% | 1M | Proprietary | ||
Claude Opus 5.5 (xhigh) | 57 | $6.05 | 16.1 | 82.33 | 0.0% | 1M | Proprietary | ||
GPT-6 Astra (max) | 57 | $6.24 | 20.8 | 231.48 | 3.5% | 1M | Proprietary | ||
GPT-6 Astra (max) | 57 | $6.46 | 20.0 | 221.92 | 1.1% | 524k | Proprietary | ||
GPT-6 Astra (max) | 57 | $6.25 | 14.1 | 178.65 | 0.0% | 524k | Proprietary | ||
GPT-6 Astra (max) (Fast) | 57 | $12.49 | 10.6 | 107.76 | 0.0% | 1M | Proprietary | ||
GPT-6 Astra (max) (Ultrafast) | 57 | $37.47 | 4.6 | 37.18 | 0.0% | 1M | Proprietary | ||
GPT-6 Astra (max) (Flex) | 57 | $3.12 | 13.6 | 173.78 | 5.2% | 1M | Proprietary | ||
GPT-6 Astra (xhigh) | 55 | $3.66 | 10.3 | 119.46 | 0.0% | 1M | Proprietary | ||
GPT-6 Astra (high) | 55 | $3.24 | 8.8 | 54.35 | 1.7% | 1M | Proprietary | ||
GPT-6.1 Sol (max) | 55 | $1.27 | 21.9 | 196.82 | 0.0% | 1M | Proprietary | ||
GPT-6.1 Sol (max) | 55 | $1.29 | 27.0 | 204.88 | 2.2% | 1M | Proprietary | ||
GPT-6.1 Sol (max) (Fast) | 55 | $2.54 | 15.0 | 117.73 | 1.9% | 1M | Proprietary | ||
GPT-6.1 Sol (max) (Flex) | 55 | $0.64 | 20.3 | 152.53 | 13.3% | 1M | Proprietary | ||
GPT-6.1 Sol (max) (Ultrafast) | 55 | $7.63 | 5.1 | 31.36 | 1.7% | 1M | Proprietary | ||
Claude Sonnet 5.5 (max) | 55 | $10.02 | 31.5 | 277.32 | 0.0% | 1M | Proprietary | ||
Claude Sonnet 5.5 (max) | 55 | $8.91 | 32.7 | 269.16 | 10.8% | 1M | Proprietary | ||
Claude Sonnet 5.5 (max) | 55 | $8.91 | 31.8 | 274.31 | 5.2% | 1M | Proprietary | ||
Claude Sonnet 5.5 (max) | 55 | $14.47 | 30.6 | 271.15 | 5.3% | 1M | Proprietary | ||
Gemini 4 Carbon (low) | 54 | $7.19 | 36.3 | 8.38 | 29.4% | 1M | Proprietary | ||
GPT-6.1 Sol (xhigh) | 52 | $0.76 | 10.1 | 75.96 | 6.1% | 1M | Proprietary | ||
Claude Opus 5.5 (high) | 52 | $3.46 | 9.3 | 35.35 | 0.0% | 1M | Proprietary | ||
GPT-6 Astra (medium) | 52 | $2.73 | 6.5 | 6.73 | 0.8% | 1M | Proprietary | ||
GPT-6.1 Terra (max) | 51 | $0.96 | 13.7 | 172.24 | 3.2% | 1M | Proprietary | ||
Gemini 4 Argon (high) AI Studio | 50 | $9.95 | 26.9 | 38.00 | 4.8% | 1M | Proprietary | ||
Gemini 4 Argon (high) (Vertex) | 50 | $7.68 | 35.9 | 44.37 | 11.5% | 1M | Proprietary | ||
GPT-6.1 Sol (high) | 50 | $0.59 | 7.0 | 42.86 | 0.0% | 1M | Proprietary | ||
Claude Fable 5.1 (xhigh) | 50 | $10.85 | 18.8 | 67.07 | 0.0% | 1M | Proprietary | ||
Claude Sonnet 5.5 (xhigh) | 50 | $4.09 | 14.9 | 31.07 | 0.0% | 1M | Proprietary | ||
Claude Fable 5.1 (max) | 49 | $12.99 | 22.5 | 188.03 | 0.0% | 1M | Proprietary | ||
Claude Opus 5.5 (medium) | 48 | $2.45 | 6.8 | 18.13 | 0.0% | 1M | Proprietary | ||
Claude Fable 5.1 (high) | 47 | $7.54 | 12.7 | 15.85 | 0.0% | 1M | Proprietary | ||
Kimi K3.1 Pro | 46 | $3.68 | 36.6 | 165.49 | 1.0% | 1M | Open | ||
Kimi K3.1 Pro | 46 | $4.68 | 26.0 | 86.63 | 0.0% | 1M | Open | ||
Kimi K3.1 Pro | 46 | $3.50 | 13.1 | 80.64 | 12.9% | 1M | Open | ||
Kimi K3.1 Pro | 46 | $3.59 | 17.9 | 86.88 | 0.0% | 1M | Open | ||
Kimi K3.1 Pro | 46 | $3.26 | 10.4 | 34.96 | 9.6% | 1M | Open | ||
Kimi K3.1 Pro | 46 | $4.39 | 52.1 | 171.42 | 2.3% | 1M | Open | ||
Kimi K3.1 Pro | 46 | $5.24 | 19.9 | 55.32 | 3.3% | 1M | Open | ||
Kimi K3.1 Pro (ULTRA) | 46 | $6.32 | 5.0 | 19.05 | 0.0% | 1M | Open | ||
Kimi K3.1 Pro | 46 | $9.55 | 9.5 | 34.91 | 0.0% | 1M | Open | ||
Kimi K3.1 Pro High Speed | 46 | $4.42 | 18.0 | 74.65 | 5.0% | 1M | Open | ||
Kimi K3.1 Pro | 46 | $3.19 | 9.5 | 44.93 | 0.0% | 1M | Open | ||
Kimi K3.1 Pro | 46 | $4.38 | 15.6 | 80.41 | 1.7% | 1M | Open | ||
Kimi K3.1 Pro | 46 | $4.22 | 11.6 | 42.48 | 0.0% | 1M | Open | ||
Kimi K3.1 Pro | 46 | $2.94 | 10.8 | 33.43 | 5.5% | 1M | Open | ||
Kimi K3.1 Pro | 46 | $8.10 | 5.7 | 23.99 | 0.0% | 1M | Open | ||
GPT-6.1 Sol (medium) | 46 | $0.36 | 4.2 | 6.15 | 0.0% | 1M | Proprietary | ||
GPT-6.1 Terra (xhigh) | 45 | $0.40 | 6.1 | 36.07 | 1.0% | 1M | Proprietary | ||
Muse Wonder (max) | 44 | $6.95 | 12.9 | 22.22 | 0.0% | 1M | Proprietary | ||
GPT-6 Astra (low) | 43 | $1.42 | 3.5 | 3.83 | 0.9% | 1M | Proprietary | ||
GPT-6 Astra (low) | 43 | $1.47 | 3.0 | 3.08 | 0.0% | 524k | Proprietary | ||
Claude Fable 5.1 (medium) | 43 | $5.56 | 9.5 | 9.47 | 1.5% | 1M | Proprietary | ||
GPT-6.1 Terra (high) | 42 | $0.26 | 4.0 | 11.96 | 0.0% | 1M | Proprietary | ||
Claude Sonnet 5.5 (high) | 42 | $1.64 | 7.0 | 12.36 | 0.0% | 1M | Proprietary | ||
Muse Wonder (high) | 41 | $4.56 | 9.0 | 9.32 | 0.0% | 1M | Proprietary | ||
Claude Fable 5.1 (low) | 39 | $4.47 | 7.3 | 8.17 | 0.0% | 1M | Proprietary | ||
GPT-6.1 Terra (medium) | 38 | $0.17 | 2.6 | 4.79 | 0.0% | 1M | Proprietary | ||
Claude Haiku 5.5 (max) | 36 | $0.41 | 15.8 | 181.34 | 5.7% | 1M | Proprietary | ||
Grok 4.7 (xhigh) | 35 | $7.77 | 24.3 | 53.09 | 1.5% | 500k | Proprietary | ||
Grok 4.7 (high) | 35 | $6.18 | 20.8 | 30.83 | 0.7% | 500k | Proprietary | ||
GPT-6.1 Sol (low) | 35 | $0.16 | 1.8 | 2.75 | 0.0% | 1M | Proprietary | ||
Claude Opus 5.5 (low) | 35 | $0.98 | 3.0 | 6.17 | 0.0% | 1M | Proprietary | ||
Claude Opus 5.5 (low) | 35 | $0.98 | 3.1 | 7.78 | 0.0% | 1M | Proprietary | ||
Claude Opus 5.5 (low) | 35 | $2.64 | 2.9 | 6.29 | 0.0% | 1M | Proprietary | ||
Claude Opus 5.5 (low) | 35 | $1.07 | 3.0 | 5.88 | 3.4% | 1M | Proprietary | ||
Claude Haiku 5.5 (xhigh) | 35 | $0.25 | 9.7 | 52.05 | 3.1% | 1M | Proprietary | ||
Tencent Hy4 | 35 | $1.03 | 13.9 | 103.27 | 0.0% | 1M | Proprietary | ||
Qwen3.8 Max (0902) | 34 | $10.02 | 61.3 | 133.49 | 0.9% | 984k | Proprietary | ||
DeepSeek V4.1 Flash 1017 (max) | 33 | $1.98 | 13.6 | 40.54 | 0.0% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) | 33 | $0.52 | 16.4 | 67.82 | 0.0% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) (FAST) | 33 | $2.32 | 2.4 | 7.36 | 0.0% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) | 33 | $0.70 | 5.4 | 18.94 | 2.4% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) | 33 | $0.30 | 11.1 | 38.88 | 11.3% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) | 33 | $0.56 | 11.0 | 40.11 | 0.9% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) (ULTRA CHAT) | 33 | $0.90 | 19.2 | 23.22 | 62.0% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) (ULTRA) | 33 | $0.90 | 8.2 | 32.83 | 0.9% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) | 33 | $0.39 | 12.8 | 53.36 | 3.5% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) (FAST) | 33 | $0.65 | 8.5 | 32.87 | 5.7% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) | 33 | $0.60 | 13.6 | 52.39 | 0.9% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) | 33 | $0.19 | 27.7 | 113.38 | 0.9% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) | 33 | $1.22 | 12.5 | 45.55 | 0.8% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) | 33 | $0.52 | 11.4 | 49.14 | 0.0% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) | 33 | $0.78 | 7.5 | 31.67 | 0.0% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) | 33 | $1.24 | 10.5 | 45.94 | 0.0% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) | 33 | $3.27 | 12.4 | 50.74 | 0.0% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) (FAST) | 33 | $6.36 | 7.8 | 29.70 | 0.0% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) | 33 | $0.45 | 10.0 | 37.96 | 0.0% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) | 33 | $0.83 | 12.5 | 50.73 | 0.9% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) | 33 | $0.38 | 11.6 | 49.86 | 0.8% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) | 33 | $2.37 | 16.1 | 59.88 | 0.0% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) | 33 | $1.03 | 10.6 | 43.53 | 0.9% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) | 33 | $0.57 | 12.8 | 57.11 | 0.9% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (max) | 33 | $0.84 | 13.1 | 42.73 | 0.0% | 1M | Open | ||
GLM-5.3 (max) | 32 | $4.92 | 12.3 | 53.02 | 0.0% | 1M | Open | ||
GLM-5.3 (max) | 32 | $5.01 | 31.3 | 95.86 | 2.0% | 1M | Open | ||
GLM-5.3 (max) | 32 | $4.92 | 12.8 | 37.44 | 2.8% | 1M | Open | ||
GLM-5.3 (max) | 32 | $4.92 | 11.8 | 34.06 | 3.4% | 1M | Open | ||
GLM-5.3 (max) | 32 | $2.39 | 29.3 | 106.59 | 1.0% | 1M | Open | ||
GLM-5.3 (max) | 32 | $5.10 | 12.7 | 40.27 | 2.8% | 1M | Open | ||
GLM-5.3 (max) (FAST) | 32 | $10.21 | 13.2 | 48.26 | 0.0% | 1M | Open | ||
GLM-5.3 (max) | 32 | $5.00 | 18.7 | 55.14 | 0.9% | 1M | Open | ||
GLM-5.3 (max) | 32 | $3.45 | 25.7 | 92.32 | 2.7% | 1M | Open | ||
GLM-5.3 (max) | 32 | $4.92 | 17.5 | 71.90 | 1.3% | 1M | Open | ||
GLM-5.3 (max) | 32 | $1.99 | 22.3 | 90.35 | 2.7% | 1M | Open | ||
GLM-5.3 (max) | 32 | $4.92 | 11.2 | 39.20 | 0.0% | 1M | Open | ||
GLM-5.3 (max) | 32 | $3.13 | 16.6 | 41.98 | 0.0% | 1M | Open | ||
GLM-5.3 (max) (FAST) | 32 | $9.52 | 8.2 | 26.78 | 2.7% | 1M | Open | ||
GLM-5.3 (max) (FP4) | 32 | $3.69 | 7.4 | 27.63 | 0.0% | 1M | Open | ||
GLM-5.3 (max) (FP4 ULTRA CHAT) | 32 | $7.39 | 27.1 | 34.85 | 61.2% | 1M | Open | ||
GLM-5.3 (max) | 32 | $8.89 | 30.9 | 95.97 | 2.8% | 164k | Open | ||
GLM-5.3 (max) (FP4) | 32 | $5.10 | 9.9 | 28.22 | 0.0% | 786k | Open | ||
GLM-5.3 (max) (FP4) | 32 | $2.22 | 21.7 | 54.96 | 9.0% | 1M | Open | ||
GLM-5.3 (max) | 32 | $4.53 | 17.6 | 45.22 | 2.8% | 1M | Open | ||
GLM-5.3 (max) (FP4, FAST) | 32 | $13.49 | 7.4 | 28.91 | 0.7% | 1M | Open | ||
GLM-5.3 (max) (FP4) | 32 | $4.92 | 10.8 | 32.14 | 0.0% | 1M | Open | ||
GLM-5.3 (max) | 32 | $2.53 | 21.9 | 71.18 | 4.6% | 1M | Open | ||
GLM-5.3 (max) | 32 | $2.40 | 16.4 | 51.70 | 0.0% | 1M | Open | ||
GLM-5.3 (max) | 32 | $1.48 | 21.2 | 61.98 | 0.8% | 1M | Open | ||
GLM-5.3 (max) | 32 | $34.52 | 9.8 | 18.48 | 0.0% | 262k | Open | ||
Grok 4.7 (low) | 31 | $2.92 | 10.0 | 9.57 | 0.8% | 500k | Proprietary | ||
Gemini 3.8 Flash (high) AI Studio | 31 | $7.77 | 14.6 | 20.41 | 1.7% | 1M | Proprietary | ||
Claude Sonnet 5.5 (medium) | 31 | $0.78 | 3.6 | 4.91 | 0.0% | 1M | Proprietary | ||
Inkling 2 Small | 31 | $1.18 | 16.6 | 30.27 | 0.0% | 262k | Proprietary | ||
GPT-6.1 Terra (non-reasoning) | 31 | $0.23 | 2.2 | 1.68 | 0.0% | 1M | Proprietary | ||
Gemini 3.8 Flash (medium) AI Studio | 30 | $6.26 | 12.0 | 12.10 | 0.0% | 1M | Proprietary | ||
MiMo-V2.6-Pro | 30 | $0.26 | 45.0 | 43.27 | 0.0% | 1M | Open | ||
MiMo-V2.6-Pro | 30 | $0.54 | 49.2 | 56.44 | 0.8% | 1M | Open | ||
MiMo-V2.6-Pro | 30 | $0.27 | 15.4 | 15.76 | 2.8% | 1M | Open | ||
MiMo-V2.6-Pro (BF16) | 30 | $0.24 | 51.8 | 33.20 | 8.5% | 1M | Open | ||
Claude Haiku 5.5 (high) | 30 | $0.16 | 6.7 | 23.38 | 0.0% | 1M | Proprietary | ||
Ling 3.1 Flash 1019 | 30 | $3.19 | -- | -- | -- | 1M | Open | ||
GPT-6.1 Terra (low) | 29 | $0.07 | 1.1 | 2.27 | 0.7% | 1M | Proprietary | ||
MiniMax-M3.1-Flash | 29 | $0.42 | 7.5 | 29.72 | 1.3% | 1M | Open | ||
MiniMax-M3.1-Flash | 29 | $0.33 | 15.0 | 34.11 | 4.0% | 1M | Open | ||
MiniMax-M3.1-Flash | 29 | $1.01 | 19.6 | 82.90 | 1.9% | 1M | Open | ||
MiniMax-M3.1-Flash | 29 | $3.11 | 31.2 | 112.84 | 0.0% | 1M | Open | ||
MiniMax-M3.1-Flash | 29 | $0.44 | 10.6 | 27.34 | 1.6% | 1M | Open | ||
MiniMax-M3.1-Flash | 29 | $0.46 | 19.4 | 79.32 | 0.0% | 1M | Open | ||
MiniMax-M3.1-Flash | 29 | $0.50 | 14.5 | 29.04 | 0.0% | 1M | Open | ||
MiniMax-M3.1-Flash | 29 | $1.45 | 7.6 | 19.73 | 0.0% | 262k | Open | ||
MiniMax-M3.1-Flash | 29 | $0.68 | 21.1 | 87.12 | 3.0% | 1M | Open | ||
MiniMax-M3.1-Flash | 29 | $0.43 | 13.1 | 50.59 | 0.0% | 1M | Open | ||
MiniMax-M3.1-Flash | 29 | $0.43 | 20.6 | 70.41 | 0.9% | 1M | Open | ||
MiniMax-M3.1-Flash | 29 | $2.97 | 16.9 | 52.72 | 3.2% | 1M | Open | ||
MiniMax-M3.1-Flash | 29 | $0.49 | 18.0 | 67.97 | 0.9% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (high) | 29 | $0.46 | 10.6 | 23.13 | 0.0% | 1M | Open | ||
Step 5 Preview | 29 | $2.35 | 14.6 | 25.08 | 4.9% | 1M | Open | ||
GPT-6 Luna (max) | 28 | $0.15 | 12.5 | 94.74 | 1.0% | 1M | Proprietary | ||
GPT-6 Luna (max) | 28 | $0.16 | 10.8 | 79.93 | 1.0% | 524k | Proprietary | ||
GPT-6 Luna (max) (Flex) | 28 | $0.08 | 24.3 | 144.05 | 24.5% | 1M | Proprietary | ||
GLM-5.3-Flash | 28 | $1.81 | 17.4 | 37.32 | 0.0% | 1M | Open | ||
GLM-5.3-Flash | 28 | $0.58 | 40.3 | 92.00 | 1.6% | 1M | Open | ||
GLM-5.3-Flash | 28 | $1.74 | 18.2 | 50.06 | 0.0% | 1M | Open | ||
GLM-5.3-Flash | 28 | $1.16 | 16.6 | 44.33 | 0.0% | 1M | Open | ||
GLM-5.3-Flash | 28 | $0.80 | 33.7 | 75.67 | 1.6% | 1M | Open | ||
GLM-5.3-Flash | 28 | $0.78 | 14.2 | 23.35 | 0.0% | 1M | Open | ||
GLM-5.3-Flash | 28 | $0.58 | 18.2 | 37.70 | 0.8% | 1M | Open | ||
GLM-5.3-Flash | 28 | $1.03 | 48.0 | 136.78 | 1.9% | 1M | Open | ||
GLM-5.3-Flash | 28 | $0.41 | 23.5 | 56.50 | 2.8% | 1M | Open | ||
GLM-5.3-Flash | 28 | $0.48 | 10.7 | 28.42 | 0.0% | 1M | Open | ||
GLM-5.3-Flash | 28 | $0.52 | 14.1 | 27.91 | 0.0% | 1M | Open | ||
GLM-5.3-Flash | 28 | $0.69 | 11.3 | 23.08 | 0.0% | 1M | Open | ||
GLM-5.3-Flash | 28 | $0.64 | 11.8 | 48.36 | 4.0% | 1M | Open | ||
GLM-5.3-Flash | 28 | $0.89 | 14.7 | 41.90 | 2.5% | 1M | Open | ||
GLM-5.3-Flash | 28 | $0.95 | 15.3 | 38.54 | 0.0% | 1M | Open | ||
GLM-5.3-Flash | 28 | $0.61 | 11.3 | 30.33 | 0.0% | 1M | Open | ||
GLM-5.3-Flash | 28 | $0.87 | 15.3 | 30.81 | 0.0% | 1M | Open | ||
GLM-5.3-Flash | 28 | $1.03 | 10.9 | 29.91 | 0.0% | 1M | Open | ||
GLM-5.3-Flash (FP4) | 28 | $0.94 | 12.4 | 35.84 | 0.0% | 1M | Open | ||
GLM-5.3-Flash (FAST) | 28 | $1.15 | 5.7 | 15.65 | 0.0% | 1M | Open | ||
GLM-5.3-Flash (FP4) | 28 | $0.59 | 12.3 | 47.07 | 1.6% | 1M | Open | ||
GLM-5.3-Flash (FP4, ULTRA CHAT) | 28 | $1.15 | 14.4 | 12.61 | 65.5% | 1M | Open | ||
GLM-5.3-Flash | 28 | $0.90 | 12.5 | 36.09 | 0.0% | 1M | Open | ||
GLM-5.3-Flash (FP4, ULTRA) | 28 | $1.18 | 7.8 | 19.49 | 0.0% | 1M | Open | ||
MiMo-V2.6-Flash | 27 | $0.13 | 63.7 | 49.85 | 2.3% | 1M | Open | ||
MiMo-V2.6-Flash | 27 | $0.13 | 47.6 | 41.92 | 3.8% | 1M | Open | ||
MiMo-V2.6-Flash (BF16) | 27 | $0.11 | 49.6 | 47.40 | 1.4% | 524k | Open | ||
MiMo-V2.6-Flash | 27 | $0.43 | 17.1 | 17.41 | 0.0% | 1M | Open | ||
Mistral Large 4 (high) | 26 | $2.06 | 13.9 | 34.43 | 0.0% | 1M | Open | ||
Claude Sonnet 5.5 (low) | 26 | $1.03 | 2.5 | 2.21 | 0.0% | 1M | Proprietary | ||
Claude Sonnet 5.5 (low) | 26 | $0.51 | 2.6 | 3.28 | 0.0% | 1M | Proprietary | ||
Claude Sonnet 5.5 (low) | 26 | $0.48 | 2.6 | 3.81 | 0.0% | 1M | Proprietary | ||
Claude Sonnet 5.5 (low) | 26 | $0.48 | 2.4 | 2.65 | 0.7% | 1M | Proprietary | ||
Muse Spark Open (xhigh) | 25 | $2.02 | 21.2 | 34.05 | 10.2% | 1M | Open | ||
Muse Spark Open (xhigh) | 25 | $2.81 | 4.9 | 11.46 | 0.8% | 1M | Open | ||
Muse Spark Open (xhigh) (FP4) | 25 | $1.61 | 7.5 | 13.49 | 1.4% | 1M | Open | ||
Muse Spark Open (xhigh) | 25 | $2.02 | 7.8 | 13.88 | 0.0% | 1M | Open | ||
Muse Spark Open (xhigh) (NVFP4) | 25 | $1.68 | 4.3 | 7.97 | 0.0% | 1M | Open | ||
Claude Haiku 5.5 (medium) | 25 | $0.09 | 4.1 | 10.76 | 3.8% | 1M | Proprietary | ||
GPT-6 Luna (xhigh) | 23 | $0.10 | 7.7 | 23.82 | 0.0% | 1M | Proprietary | ||
Mistral Large 4 (medium) | 23 | $1.41 | 9.7 | 21.40 | 0.0% | 1M | Open | ||
GLM-5.3 (low) | 23 | $1.57 | 17.2 | 12.12 | 0.0% | 1M | Open | ||
GLM-5.3 (low) (FP4) | 23 | $0.70 | 10.9 | 5.59 | 5.8% | 1M | Open | ||
GLM-5.3 (low) (FP4, FAST) | 23 | $4.16 | 3.4 | 3.30 | 0.0% | 1M | Open | ||
GLM-5.3 (low) | 23 | $1.55 | 7.4 | 4.01 | 0.0% | 1M | Open | ||
GLM-5.3 (low) | 23 | $0.72 | 7.7 | 4.82 | 0.0% | 1M | Open | ||
GLM-5.3 (low) | 23 | $10.22 | 5.0 | 3.77 | 0.0% | 262k | Open | ||
GLM-5.3 (low) | 23 | $3.56 | 15.6 | 10.48 | 0.0% | 164k | Open | ||
GLM-5.3 (low) (FAST) | 23 | $3.21 | 4.5 | 4.84 | 0.0% | 1M | Open | ||
DeepSeek V4 Pro 0813 (max) | 23 | $2.66 | 26.2 | 71.10 | 0.0% | 1M | Open | ||
DeepSeek V4 Pro 0813 (max) | 23 | $1.77 | 23.6 | 84.95 | 0.9% | 1M | Open | ||
DeepSeek V4 Pro 0813 (max) | 23 | $2.52 | 32.2 | 61.78 | 0.0% | 1M | Open | ||
DeepSeek V4 Pro 0813 (max) | 23 | $4.95 | 13.1 | 33.56 | 0.0% | 1M | Open | ||
DeepSeek V4 Pro 0813 (max) | 23 | $1.86 | 26.2 | 82.06 | 1.7% | 1M | Open | ||
DeepSeek V4 Pro 0813 (max) | 23 | $4.94 | 11.9 | 31.49 | 3.6% | 1M | Open | ||
DeepSeek V4 Pro 0813 (max) | 23 | $2.98 | 25.6 | 73.35 | 0.8% | 1M | Open | ||
DeepSeek V4 Pro 0813 (max) | 23 | $1.49 | 7.3 | 21.19 | 0.0% | 1M | Open | ||
DeepSeek V4 Pro 0813 (max) | 23 | $13.43 | 15.1 | 39.89 | 0.0% | 1M | Open | ||
Gemini 3.8 Flash (low) AI Studio | 23 | -- | -- | 2.51 | 0.0% | 1M | Proprietary | ||
GPT-6 Luna (high) | 21 | $0.07 | 5.8 | 12.62 | 0.0% | 1M | Proprietary | ||
GPT-6 Luna (high) | 21 | $0.08 | -- | -- | -- | 524k | Proprietary | ||
Qwen3.8 27B (xhigh) | 20 | $1.54 | 45.2 | 194.07 | 2.3% | 262k | Open | ||
Qwen3.8 27B (xhigh) (FP8) | 20 | $3.30 | 30.5 | 163.83 | 2.7% | 262k | Open | ||
Qwen3.8 27B (xhigh) | 20 | $3.53 | 41.4 | 121.51 | 2.2% | 1M | Open | ||
Qwen3.8 27B (xhigh) (FP8) | 20 | $1.78 | 24.6 | 74.97 | 4.6% | 262k | Open | ||
Qwen3.8 27B (xhigh) | 20 | $1.47 | 8.0 | 28.33 | 0.8% | 262k | Open | ||
Qwen3.8 27B (xhigh) | 20 | $1.05 | 17.7 | 64.26 | 0.0% | 262k | Open | ||
Qwen3.8 27B (xhigh) | 20 | $2.61 | 13.3 | 49.15 | 0.9% | 262k | Open | ||
Qwen3.8 27B (xhigh) (FP4) | 20 | $1.98 | 6.7 | 20.74 | 0.0% | 262k | Open | ||
Qwen3.8 27B (xhigh) (NVFP4) | 20 | $0.00 | 12.9 | 39.73 | 0.9% | 262k | Open | ||
Qwen3.8 27B (xhigh) | 20 | $2.73 | 95.3 | 311.36 | 20.2% | 262k | Open | ||
MiniMax-M3 (MXFP8) | 19 | $1.17 | 13.0 | 10.88 | 2.3% | 1M | Open | ||
MiniMax-M3 (NVFP4) | 19 | $1.48 | 6.5 | 8.60 | 0.0% | 262k | Open | ||
MiniMax-M3 | 19 | $1.49 | 20.2 | 21.57 | 1.6% | 1M | Open | ||
MiniMax-M3 | 19 | $1.16 | 14.7 | 88.82 | 1.0% | 1M | Open | ||
MiniMax-M3 | 19 | $1.15 | 13.1 | 8.91 | 0.0% | 1M | Open | ||
MiniMax-M3 (FP8) | 19 | $1.30 | 7.0 | 4.79 | 0.0% | 1M | Open | ||
MiniMax-M3 (FP8) | 19 | $1.14 | 14.7 | 88.32 | 0.0% | 1M | Open | ||
MiniMax-M3 | 19 | $1.29 | 13.6 | 84.07 | 0.0% | 512k | Open | ||
MiniMax-M3 | 19 | $1.11 | 45.4 | 43.10 | 4.3% | 524k | Open | ||
MiniMax-M3 | 19 | $0.91 | 15.3 | 2.18 | 0.0% | 1M | Open | ||
MiniMax-M3 | 19 | $1.26 | 6.8 | 3.32 | 3.6% | 524k | Open | ||
Claude Haiku 5.5 (low) | 19 | $0.04 | 2.2 | 8.72 | 0.0% | 1M | Proprietary | ||
DeepSeek V4.1 Flash 1017 (non-reasoning) | 19 | $0.43 | 7.3 | 1.32 | 1.4% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (non-reasoning) (FAST) | 19 | -- | 3.7 | 3.80 | 0.0% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (non-reasoning) | 19 | $0.63 | 7.4 | 1.23 | 0.0% | 1M | Open | ||
DeepSeek V4.1 Flash 1017 (non-reasoning) | 19 | $2.09 | 4.8 | 0.96 | 0.0% | 1M | Open | ||
GPT-6 Luna (medium) | 18 | $0.04 | 3.3 | 6.23 | 0.0% | 1M | Proprietary | ||
K2 Horizon 375B A23B | 18 | $0.00 | 5.0 | 21.73 | 0.8% | 524k | Open | ||
Beam 1.0 (NVFP4) | 18 | $0.45 | 1.2 | 5.22 | 0.0% | 1M | Open | ||
Beam 1.0 (NVFP4) | 18 | $0.70 | 2.6 | 8.28 | 0.0% | 1M | Open | ||
Beam 1.0 (NVFP4) | 18 | $0.28 | 2.5 | 11.95 | 2.5% | 1M | Open | ||
Beam 1.0 | 18 | $0.28 | 2.8 | 8.42 | 0.0% | 1M | Open | ||
Beam 1.0 (NVFP4) | 18 | $0.65 | 1.9 | 7.48 | 0.0% | 1M | Open | ||
Qwen3.8 27B (medium) | 17 | $2.16 | 31.9 | 37.16 | 0.0% | 1M | Open | ||
Qwen3.8 27B (low) | 16 | $1.91 | 27.2 | 19.18 | 0.0% | 1M | Open | ||
Nemotron 3.5 Super VL (NVFP4) | 14 | $0.45 | 3.8 | 9.10 | 0.0% | 1M | Open | ||
Nemotron 3.5 Super VL | 14 | $0.35 | 4.4 | 10.64 | 1.7% | 1M | Open | ||
Nemotron 3.5 Super VL | 14 | $0.31 | 2.7 | 6.78 | 0.0% | 1M | Open | ||
Nemotron 3.5 Super VL | 14 | $0.84 | 6.7 | 21.69 | 2.5% | 1M | Open | ||
Nemotron 3.5 Super VL (NVFP4) | 14 | $0.47 | 9.1 | 32.98 | 0.0% | 1M | Open | ||
Nemotron 3.5 Super VL | 14 | $0.94 | 9.3 | 20.94 | 0.0% | 131k | Open | ||
Nemotron 3.5 Super VL | 14 | $0.52 | 19.7 | 22.63 | 52.8% | 262k | Open | ||
Nemotron 3.5 Super VL (NVFP4) | 14 | $0.61 | 4.2 | 10.20 | 0.0% | 262k | Open | ||
Inkling Small | 13 | $0.29 | 4.3 | 48.99 | 2.9% | 524k | Open | ||
Inkling Small | 13 | $0.20 | 5.0 | 20.15 | 1.0% | 256k | Open | ||
DeepSeek V4 Pro 0813 (non-reasoning) | 13 | $0.78 | 6.2 | 2.76 | 0.0% | 1M | Open | ||
DeepSeek V4 Pro 0813 (non-reasoning) | 13 | $0.98 | 15.3 | 2.62 | 0.0% | 1M | Open | ||
DeepSeek V4 Pro 0813 (non-reasoning) | 13 | $6.52 | 11.8 | 2.65 | 0.0% | 1M | Open | ||
DeepSeek V4 Pro 0813 (non-reasoning) | 13 | $2.31 | 9.7 | 17.47 | 2.4% | 1M | Open | ||
Inkling (xhigh) (FP8) | 12 | $1.26 | 6.6 | 84.73 | 1.9% | 131k | Open | ||
Inkling (xhigh) | 12 | $2.74 | 11.4 | 30.04 | 2.0% | 524k | Open | ||
Inkling (xhigh) (NVFP4) | 12 | $1.99 | 7.0 | 19.63 | 0.0% | 1M | Open | ||
Inkling (xhigh) | 12 | $1.35 | 8.3 | 20.16 | 2.1% | 262k | Open | ||
Inkling (xhigh) | 12 | $1.44 | 5.9 | 16.22 | 0.0% | 1M | Open | ||
Nemotron 3 Ultra | 12 | $3.16 | 2.8 | 2.93 | 0.0% | 262k | Open | ||
Nemotron 3 Ultra | 12 | $1.74 | 10.5 | 7.01 | 0.0% | 262k | Open | ||
Nemotron 3 Ultra BF16 | 12 | $4.03 | 12.2 | 13.24 | 0.0% | 262k | Open | ||
Nemotron 3 Ultra | 12 | $3.81 | 3.9 | 4.17 | 0.0% | 256k | Open | ||
Nemotron 3 Ultra | 12 | $2.21 | 6.0 | 6.42 | 0.0% | 262k | Open | ||
Gemini 3.5 Flash-Lite AI Studio | 12 | $0.69 | 1.7 | 5.10 | 1.7% | 1M | Proprietary | ||
Qwen3.8 27B (non-reasoning) | 10 | $3.77 | 17.7 | 5.17 | 0.0% | 1M | Open | ||
Qwen3.8 27B (non-reasoning) | 10 | $1.95 | 3.5 | 1.65 | 0.0% | 262k | Open | ||
Qwen3.8 27B (non-reasoning) | 10 | $1.18 | 6.9 | 3.92 | 0.0% | 262k | Open | ||
Qwen3.8 27B (non-reasoning) | 10 | $3.31 | 5.7 | 1.55 | 0.0% | 262k | Open | ||
Qwen3.8 27B (non-reasoning) (NVFP4) | 10 | $0.00 | 4.9 | 2.22 | 5.6% | 262k | Open | ||
Qwen3.8 27B (non-reasoning) (FP4) | 10 | $2.33 | 2.7 | 1.98 | 0.0% | 262k | Open | ||
Qwen3.8 27B (non-reasoning) | 10 | $3.40 | 15.8 | 4.65 | 0.0% | 262k | Open | ||
GPT-6 Luna (low) | 10 | $0.01 | 0.6 | 2.53 | 0.0% | 1M | Proprietary | ||
GPT-6 Luna (non-reasoning) | 9 | $0.07 | 1.9 | 1.09 | 0.7% | 1M | Proprietary | ||
GPT-6 Luna (non-reasoning) | 9 | $0.08 | 1.8 | 1.36 | 0.0% | 524k | Proprietary | ||
Muse Glimmer (high) | 6 | $0.23 | 4.6 | 20.30 | 0.0% | 131k | Open | ||
Muse Glimmer (high) | 6 | $0.13 | 4.9 | 26.81 | 1.7% | 131k | Open | ||
Muse Glimmer (high) | 6 | $0.06 | 3.1 | 13.61 | 1.8% | 131k | Open | ||
Command A+ | 6 | $0.00 | 3.4 | 21.96 | 2.6% | 200k | Open | ||
Nemotron 3.5 Lightning (NVFP4) | 6 | $0.31 | 5.0 | 19.58 | 0.0% | 262k | Open | ||
Nemotron 3.5 Lightning (BF16) | 6 | $0.32 | 6.8 | 28.26 | 1.7% | 1M | Open | ||
Nemotron 3.5 Lightning (BF16) | 6 | $0.24 | 4.4 | 13.15 | 0.9% | 262k | Open | ||
Nemotron 3.5 Lightning (BF16) | 6 | $0.07 | 3.9 | 12.19 | 14.6% | 262k | Open | ||
Nemotron 3.5 Lightning (NVFP4) | 6 | $0.55 | 2.4 | 6.85 | 0.0% | 1M | Open | ||
Nemotron 3.5 Lightning (BF16) | 6 | $0.26 | 4.3 | 20.77 | 3.1% | 262k | Open | ||
Granite 4.2 8B | 5 | $0.09 | 10.6 | 36.32 | 1.0% | 131k | Open | ||
Granite 4.2 8B | 5 | $0.04 | 12.9 | 86.31 | 2.3% | 131k | Open | ||
Mistral Medium 3.5 | 5 | $1.04 | 4.8 | 27.71 | 0.0% | 262k | Open | ||
Gemma 4 31B | 4 | -- | -- | 7.76 | 0.7% | 262k | Open | ||
Gemma 4 31B (NVFP4) | 4 | -- | -- | 5.33 | 0.0% | 262k | Open | ||
Gemma 4 31B | 4 | -- | -- | 61.31 | 0.0% | 262k | Open | ||
Gemma 4 31B (AI Studio) | 4 | -- | -- | 64.29 | 1.4% | 262k | Open | ||
Gemma 4 31B | 4 | -- | -- | 30.28 | 2.8% | 262k | Open | ||
Gemma 4 31B | 4 | -- | -- | 72.52 | 0.7% | 262k | Open | ||
Gemma 4 31B | 4 | -- | -- | 37.70 | 4.2% | 262k | Open | ||
Gemma 4 31B (FP8) | 4 | -- | -- | 17.38 | 3.4% | 262k | Open | ||
Gemma 4 31B | 4 | -- | -- | 14.87 | 1.3% | 131k | Open | ||
Gemma 4 31B | 4 | -- | -- | 10.71 | 0.0% | 256k | Open | ||
Gemma 4 31B | 4 | -- | -- | 58.31 | 0.9% | 262k | Open | ||
Mistral Small 4 | 4 | $0.04 | 1.7 | 13.55 | 2.1% | 256k | Open | ||
North Mini Code | 3 | $0.00 | 4.1 | 9.10 | 0.0% | 256k | Open | ||
Qwen3.5 Omni Plus | -- | -- | -- | 2.83 | 0.0% | 256k | Proprietary | ||
Qwen3.5 122B A10B (non-reasoning) (FP4) | -- | -- | -- | 2.09 | 2.4% | 262k | Open | ||
Qwen3.5 122B A10B (non-reasoning) | -- | -- | -- | 4.42 | 0.0% | 262k | Open | ||
Gemma 4 12B (non-reasoning) | -- | -- | -- | 3.87 | 1.4% | 262k | Open | ||
Apodex 1.1 | -- | -- | -- | 14.06 | 0.0% | 256k | Proprietary | ||
Qwen3 Omni 30B A3B | -- | -- | -- | 1.30 | 0.0% | 66k | Open | ||
Nova 2.0 Pro Preview (medium) | -- | -- | -- | 17.81 | 0.0% | 256k | Proprietary | ||
Qwen3.5 397B A17B | -- | -- | -- | 61.06 | 0.9% | 262k | Open | ||
Qwen3.5 397B A17B | -- | -- | -- | 24.92 | 7.3% | 262k | Open | ||
Qwen3.5 397B A17B (FP8) | -- | -- | -- | 59.84 | 0.0% | 262k | Open | ||
Qwen3.5 397B A17B | -- | -- | -- | 44.64 | 0.0% | 262k | Open | ||
Qwen3.5 397B A17B | -- | -- | -- | 397.87 | 35.8% | 131k | Open | ||
Mistral Small 4 (non-reasoning) | -- | -- | -- | 1.77 | 0.9% | 262k | Open | ||
Solar Pro 4 | -- | -- | -- | 50.33 | 2.4% | 512k | Proprietary | ||
gpt-oss-20b (low) | -- | -- | -- | 1.45 | 1.4% | 131k | Open | ||
gpt-oss-20b (low) | -- | -- | -- | 3.24 | 0.0% | 131k | Open | ||
gpt-oss-20b (low) | -- | -- | -- | 16.53 | 2.8% | 131k | Open | ||
o3 | -- | -- | -- | 19.81 | 0.8% | 200k | Proprietary | ||
o3 | -- | -- | -- | 7.74 | 0.0% | 200k | Proprietary | ||
Qwen3.5 9B (non-reasoning) (FP8) | -- | -- | -- | 1.02 | 0.0% | 262k | Open | ||
Qwen3.5 122B A10B (FP8) | -- | -- | -- | 35.21 | 2.7% | 262k | Open | ||
Qwen3.5 122B A10B (FP4) | -- | -- | -- | 92.85 | 1.0% | 262k | Open | ||
Qwen3.5 122B A10B | -- | -- | -- | 18.83 | 0.0% | 262k | Open | ||
Qwen3.5 122B A10B | -- | -- | -- | 22.44 | 0.0% | 262k | Open | ||
Nemotron 3 Nano (non-reasoning) (FP4) | -- | -- | -- | 1.90 | 0.0% | 262k | Open | ||
Nemotron 3 Nano (non-reasoning) | -- | -- | -- | 0.91 | 0.8% | 262k | Open | ||
Nemotron 3 Nano (non-reasoning) (FP8) | -- | -- | -- | 0.75 | 7.0% | 262k | Open | ||
Qwen3 Next 80B A3B | -- | -- | -- | 1.43 | 0.0% | 262k | Open | ||
Qwen3 Next 80B A3B | -- | -- | -- | 22.50 | 0.0% | 262k | Open | ||
Qwen3 Next 80B A3B | -- | -- | -- | 1.04 | 0.0% | 262k | Open | ||
Phi-4 Multimodal | -- | -- | -- | 0.36 | 50.0% | 4k | Open | ||
Qwen3.5 9B (FP8) | -- | -- | -- | 66.36 | 5.0% | 262k | Open | ||
Qwen3.5 9B (FP8) | -- | -- | -- | 16.73 | 1.9% | 262k | Open | ||
NVIDIA Nemotron Nano 9B V2 (non-reasoning) | -- | -- | -- | 1.51 | 1.7% | 131k | Open | ||
NVIDIA Nemotron Nano 9B V2 (non-reasoning) | -- | -- | -- | 1.46 | 2.8% | 131k | Open | ||
Qwen3.5 4B (non-reasoning) FP8 | -- | -- | -- | 2.05 | 0.0% | 262k | Open | ||
Qwen3.5 397B A17B (non-reasoning) (FP8) | -- | -- | -- | 2.08 | 0.0% | 262k | Open | ||
Qwen3.5 397B A17B (non-reasoning) | -- | -- | -- | 2.57 | 0.0% | 262k | Open | ||
Qwen3.5 397B A17B (non-reasoning) | -- | -- | -- | 218.35 | 26.9% | 131k | Open | ||
Qwen3.5 397B A17B (non-reasoning) | -- | -- | -- | 2.71 | 1.5% | 262k | Open | ||
Nova Micro | -- | -- | -- | 1.35 | 0.0% | 130k | Proprietary | ||
gpt-oss-20b (high) | -- | -- | -- | 70.21 | 3.7% | 131k | Open | ||
gpt-oss-20b (high) | -- | -- | -- | 31.48 | 0.0% | 131k | Open | ||
gpt-oss-20b (high) | -- | -- | -- | 53.64 | 0.9% | 131k | Open | ||
gpt-oss-20b (high) | -- | -- | -- | 7.31 | 5.1% | 131k | Open | ||
Command A | -- | -- | -- | 7.66 | 0.9% | 288k | Open | ||
Command A | -- | -- | -- | 12.54 | 7.5% | 256k | Open | ||
Sarvam 105B (high) | -- | -- | -- | 8.68 | 7.1% | 128k | Open | ||
Gemma 4 E4B (non-reasoning) | -- | -- | -- | 1.67 | 0.7% | 131k | Open | ||
GPT-5.3 Codex (xhigh) | -- | -- | -- | 55.99 | 0.9% | 400k | Proprietary | ||
LongCat 2.0 (FP8) | -- | -- | -- | 39.82 | 2.3% | 262k | Open | ||
Llama 3.2 11B (Vision) | -- | -- | -- | 3.74 | 0.7% | 131k | Open | ||
Nova 2.0 Lite (high) | -- | -- | -- | 19.14 | 2.1% | 1M | Proprietary | ||
Solar Mini 4 | -- | -- | -- | 54.56 | 2.3% | 524k | Proprietary | ||
Qwen3.5 4B (FP8) | -- | -- | -- | 77.96 | 0.0% | 262k | Open | ||
Qwen3.6 35B A3B (non-reasoning) | -- | -- | -- | 1.37 | 1.6% | 262k | Open | ||
Qwen3.6 35B A3B (non-reasoning) (FP8) | -- | -- | -- | 2.25 | 0.8% | 262k | Open | ||
Qwen3.6 35B A3B (non-reasoning) (FP8) | -- | -- | -- | 1.36 | 0.0% | 262k | Open | ||
Qwen3.6 35B A3B (non-reasoning) | -- | -- | -- | 3.10 | 4.3% | 205k | Open | ||
Qwen3.6 35B A3B (non-reasoning) FP8 | -- | -- | -- | 2.86 | 0.0% | 262k | Open | ||
Qwen3.6 35B A3B (non-reasoning) (FP8) | -- | -- | -- | 1.16 | 2.3% | 262k | Open | ||
Qwen3.6 35B A3B (non-reasoning) | -- | -- | -- | 2.98 | 0.0% | 262k | Open | ||
Ministral 3 3B | -- | -- | -- | 1.49 | 0.8% | 256k | Open | ||
Ministral 3 3B | -- | -- | -- | 1.54 | 13.0% | 131k | Open | ||
Gemma 4 26B A4B | -- | -- | -- | 32.24 | 0.7% | 262k | Open | ||
Gemma 4 26B A4B AI Studio | -- | -- | -- | 24.14 | 1.5% | 262k | Open | ||
Gemma 4 26B A4B | -- | -- | -- | 4.63 | 0.0% | 131k | Open | ||
Gemma 4 26B A4B | -- | -- | -- | 39.95 | 0.0% | 262k | Open | ||
Gemma 4 26B A4B (FP8) | -- | -- | -- | 29.35 | 0.7% | 262k | Open | ||
Gemma 4 26B A4B | -- | -- | -- | 13.84 | 0.0% | 256k | Open | ||
Gemma 4 26B A4B | -- | -- | -- | 12.81 | 0.0% | 1M | Open | ||
Qwen3.5 Omni Flash | -- | -- | -- | 2.93 | 0.0% | 256k | Proprietary | ||
Nova 2.0 Lite (low) | -- | -- | -- | 9.67 | 0.0% | 1M | Proprietary | ||
Magistral Small 1.2 | -- | -- | -- | 2.72 | 0.0% | 128k | Open | ||
Gemma 4 26B A4B (non-reasoning) | -- | -- | -- | 1.92 | 1.4% | 262k | Open | ||
Gemma 4 26B A4B (non-reasoning) | -- | -- | -- | 1.38 | 0.0% | 131k | Open | ||
Gemma 4 26B A4B (non-reasoning) (FP8) | -- | -- | -- | 3.31 | 0.7% | 262k | Open | ||
Gemma 4 26B A4B (non-reasoning) | -- | -- | -- | 1.61 | 0.7% | 262k | Open | ||
Gemma 4 26B A4B (non-reasoning) (FP8) | -- | -- | -- | 1.56 | 0.8% | 262k | Open | ||
Gemma 4 26B A4B (non-reasoning) | -- | -- | -- | 1.68 | 0.7% | 262k | Open | ||
Gemma 4 26B A4B (non-reasoning) | -- | -- | -- | 1.35 | 0.0% | 1M | Open | ||
Gemma 4 26B A4B (non-reasoning) | -- | -- | -- | 1.35 | 0.7% | 262k | Open | ||
Ministral 3 14B | -- | -- | -- | 2.85 | 8.7% | 262k | Open | ||
Ministral 3 14B | -- | -- | -- | 1.30 | 0.8% | 256k | Open | ||
Ministral 3 14B | -- | -- | -- | 0.70 | 12.0% | 262k | Open | ||
Mercury 2.5 | -- | -- | -- | 2.33 | 1.3% | 256k | Proprietary | ||
Nova 2.0 Lite (non-reasoning) | -- | -- | -- | 1.67 | 0.8% | 1M | Proprietary | ||
Nemotron 3 Nano | -- | -- | -- | 8.60 | 1.5% | 262k | Open | ||
Nemotron 3 Nano (FP4) | -- | -- | -- | 8.27 | 0.0% | 262k | Open | ||
Nemotron 3 Nano | -- | -- | -- | 1.01 | 0.0% | 262k | Open | ||
Nemotron 3 Nano (FP8) | -- | -- | -- | 19.66 | 7.6% | 262k | Open | ||
DeepSeek V4 Flash Vision (max) | -- | -- | -- | 122.71 | 0.0% | 1M | Proprietary | ||
DeepSeek V4 Flash Vision (max) | -- | -- | -- | 56.58 | 0.0% | 1M | Proprietary | ||
DeepSeek V4 Flash Vision (max) | -- | -- | -- | 50.44 | 0.0% | 1M | Proprietary | ||
Ling 3.0 Tiny | -- | -- | -- | 38.09 | 0.0% | 262k | Open | ||
Celeris-1 | -- | -- | -- | 0.69 | 0.0% | 131k | Proprietary | ||
Tiny Aya Global | -- | -- | -- | 0.28 | 0.0% | 8k | Open | ||
Hermes 4 405B (FP8) | -- | -- | -- | 19.38 | 18.0% | 128k | Open | ||
Qwen3.6 35B A3B | -- | -- | -- | 31.98 | 4.6% | 229k | Open | ||
Qwen3.6 35B A3B (FP8) | -- | -- | -- | 32.88 | 0.0% | 262k | Open | ||
Qwen3.6 35B A3B (FP8) | -- | -- | -- | 30.03 | 1.8% | 262k | Open | ||
Qwen3.6 35B A3B (FP8) | -- | -- | -- | 30.18 | 0.0% | 262k | Open | ||
Qwen3.6 35B A3B FP8 | -- | -- | -- | 44.93 | 0.9% | 262k | Open | ||
Qwen3.6 35B A3B | -- | -- | -- | 24.83 | 5.9% | 262k | Open | ||
Qwen3.6 35B A3B | -- | -- | -- | 30.49 | 6.3% | 205k | Open | ||
Qwen3.6 35B A3B | -- | -- | -- | 14.93 | 0.0% | 262k | Open | ||
Nemotron 3 Nano Omni 30B A3B | -- | -- | -- | 8.57 | 0.0% | 66k | Open | ||
Kimi K2.7 Code (FP8) | -- | -- | -- | 33.31 | 0.0% | 66k | Open | ||
Kimi K2.7 Code | -- | -- | -- | 73.15 | 1.0% | 262k | Open | ||
Kimi K2.7 Code | -- | -- | -- | 44.59 | 0.8% | 262k | Open | ||
Kimi K2.7 Code | -- | -- | -- | 43.19 | 0.9% | 262k | Open | ||
Kimi K2.7 Code | -- | -- | -- | 46.75 | 0.0% | 256k | Open | ||
Qwen3.8 2.4T A95B | -- | -- | -- | 54.27 | 7.4% | 262k | Open | ||
Qwen3.8 2.4T A95B | -- | -- | -- | 87.51 | 0.0% | 262k | Open | ||
Qwen3.8 2.4T A95B | -- | -- | -- | 33.69 | 0.8% | 1M | Open | ||
Qwen3.8 2.4T A95B | -- | -- | -- | 125.19 | 5.3% | 262k | Open | ||
Qwen3.8 2.4T A95B | -- | -- | -- | 138.60 | 0.0% | 262k | Open | ||
Llama 4 Maverick (FP8) | -- | -- | -- | 2.39 | 0.0% | 1M | Open | ||
Llama 4 Maverick (FP8) | -- | -- | -- | 7.76 | 6.8% | 128k | Open | ||
Llama 4 Maverick | -- | -- | -- | 1.05 | 0.0% | 128k | Open | ||
Llama 4 Maverick (FP8) | -- | -- | -- | 1.61 | 0.8% | 1M | Open | ||
Llama 4 Maverick | -- | -- | -- | 1.65 | 0.0% | 128k | Open | ||
Llama 4 Maverick (FP8) | -- | -- | -- | 1.06 | 3.4% | 1M | Open | ||
GPT-6 Sol (Daybreak Blue, max) | -- | -- | -- | -- | -- | 1M | Proprietary | ||
Ministral 3 8B | -- | -- | -- | 1.83 | 0.8% | 256k | Open | ||
Ministral 3 8B | -- | -- | -- | 2.21 | 1.1% | 262k | Open | ||
Llama 3.3 70B | -- | -- | -- | 1.36 | 1.3% | 131k | Open | ||
Llama 3.3 70B | -- | -- | -- | 4.70 | 3.3% | 131k | Open | ||
Llama 3.3 70B | -- | -- | -- | 1.12 | 2.4% | 128k | Open | ||
Llama 3.3 70B (FP8) | -- | -- | -- | 7.53 | 4.7% | 131k | Open | ||
Llama 3.3 70B | -- | -- | -- | 1.77 | 0.0% | 128k | Open | ||
Llama 3.3 70B | -- | -- | -- | 1.42 | 6.5% | 128k | Open | ||
Llama 3.3 70B (Turbo, FP8) | -- | -- | -- | 6.95 | 0.0% | 131k | Open | ||
Llama 3.3 70B | -- | -- | -- | 1.01 | 0.0% | 100k | Open | ||
Llama 3.3 70B | -- | -- | -- | 2.60 | 0.0% | 128k | Open | ||
Qwen3.8-Flash-Next | -- | -- | -- | 115.87 | 1.0% | 1M | Open | ||
Phi-4 Mini | -- | -- | -- | 4.59 | 37.9% | 128k | Open | ||
Nova 2.0 Pro Preview (non-reasoning) | -- | -- | -- | 1.47 | 0.0% | 256k | Proprietary | ||
Ling 3.1 Flash | -- | -- | -- | 140.51 | 7.7% | 262k | Open | ||
Ling 3.1 Flash | -- | -- | -- | 19.12 | 0.0% | 1M | Open | ||
Qwen3.7 Plus | -- | -- | -- | 43.95 | 0.0% | 1M | Proprietary | ||
NVIDIA Nemotron Nano 12B v2 VL (non-reasoning) | -- | -- | -- | 1.48 | 0.0% | 128k | Open | ||
Llama 4 Scout | -- | -- | -- | 1.28 | 0.0% | 128k | Open | ||
Llama 4 Scout Vertex | -- | -- | -- | 1.40 | 4.1% | 1M | Open | ||
Llama 4 Scout | -- | -- | -- | 1.16 | 7.4% | 131k | Open | ||
Llama 4 Scout | -- | -- | -- | 43.11 | 23.3% | 131k | Open | ||
Llama 4 Scout | -- | -- | -- | 1.09 | 0.0% | 128k | Open | ||
Hy3 (FP8) | -- | -- | -- | 38.55 | 1.8% | 256k | Open | ||
Hy3 | -- | -- | -- | 49.05 | 0.0% | 262k | Open | ||
Hy3 (FP8) | -- | -- | -- | 183.89 | 9.6% | 262k | Open | ||
Hy3 | -- | -- | -- | 44.26 | 3.5% | 262k | Open | ||
Qwen3 Omni 30B A3B | -- | -- | -- | 24.64 | 0.0% | 66k | Open | ||
Gemini 3.1 Pro Preview (Vertex) | -- | -- | -- | 24.46 | 0.9% | 1M | Proprietary | ||
Gemini 3.1 Pro Preview (AI Studio) | -- | -- | -- | 17.84 | 0.8% | 1M | Proprietary | ||
GPT-5.5 Instant (June 2026) | -- | -- | -- | 1.29 | 0.0% | 400k | Proprietary | ||
gpt-oss-120b (low) Base | -- | -- | -- | 1.93 | 8.7% | 128k | Open | ||
gpt-oss-120b (low) | -- | -- | -- | 2.46 | 2.9% | 131k | Open | ||
gpt-oss-120b (low) Vertex | -- | -- | -- | 16.16 | 12.7% | 131k | Open | ||
gpt-oss-120b (low) | -- | -- | -- | 1.20 | 3.0% | 131k | Open | ||
gpt-oss-120b (low) | -- | -- | -- | 1.27 | 0.0% | 131k | Open | ||
gpt-oss-120b (low) | -- | -- | -- | 5.15 | 6.5% | 131k | Open | ||
gpt-oss-120b (low) | -- | -- | -- | 2.87 | 1.7% | 131k | Open | ||
gpt-oss-120b (low) | -- | -- | -- | 0.65 | 0.7% | 131k | Open | ||
gpt-oss-120b (low) | -- | -- | -- | 2.08 | 0.0% | 131k | Open | ||
gpt-oss-120b (low) | -- | -- | -- | 0.64 | 0.8% | 128k | Open | ||
gpt-oss-120b (low) | -- | -- | -- | 2.39 | 5.7% | 131k | Open | ||
gpt-oss-120b (low) | -- | -- | -- | 3.12 | 5.1% | 131k | Open | ||
gpt-oss-120b (low) | -- | -- | -- | 2.51 | 7.8% | 131k | Open | ||
gpt-oss-120b (low) | -- | -- | -- | 6.40 | 1.8% | 131k | Open | ||
Gemma 4 31B (non-reasoning) (NVFP4) | -- | -- | -- | 1.04 | 0.7% | 262k | Open | ||
Gemma 4 31B (non-reasoning) | -- | -- | -- | 2.42 | 7.6% | 262k | Open | ||
Gemma 4 31B (non-reasoning) | -- | -- | -- | 2.47 | 0.0% | 262k | Open | ||
Gemma 4 31B (non-reasoning) | -- | -- | -- | 8.28 | 0.7% | 262k | Open | ||
Gemma 4 31B (non-reasoning) (FP8) | -- | -- | -- | 3.77 | 4.5% | 262k | Open | ||
Gemma 4 31B (non-reasoning) | -- | -- | -- | 10.05 | 3.4% | 131k | Open | ||
Gemma 4 31B (non-reasoning) | -- | -- | -- | 3.74 | 2.8% | 262k | Open | ||
Gemma 4 31B (non-reasoning) | -- | -- | -- | 4.42 | 0.7% | 262k | Open | ||
Gemma 4 31B (non-reasoning) | -- | -- | -- | 9.20 | 1.0% | 262k | Open | ||
Gemma 4 31B (non-reasoning) (FP8) | -- | -- | -- | 4.01 | 0.7% | 262k | Open | ||
Hermes 4 405B (non-reasoning) (FP8) | -- | -- | -- | 5.22 | 13.1% | 128k | Open | ||
Gemma 4 E4B | -- | -- | -- | 49.74 | 0.8% | 131k | Open | ||
Reka Flash 3 | -- | -- | -- | 7.76 | 28.0% | 54k | Open | ||
Ring-2.6-1T | -- | -- | -- | 8.11 | 0.0% | 262k | Open | ||
Phi-4 | -- | -- | -- | 2.20 | 0.0% | 16k | Open | ||
Phi-4 | -- | -- | -- | 0.58 | 0.0% | 16k | Open | ||
gpt-oss-120b (high) | -- | -- | -- | 4.87 | 4.3% | 131k | Open | ||
gpt-oss-120b (high) | -- | -- | -- | 25.03 | 0.0% | 128k | Open | ||
gpt-oss-120b (high) | -- | -- | -- | 30.45 | 7.3% | 131k | Open | ||
gpt-oss-120b (high) | -- | -- | -- | 19.91 | 1.0% | 131k | Open | ||
gpt-oss-120b (high) (Turbo) | -- | -- | -- | 57.78 | 1.0% | 131k | Open | ||
gpt-oss-120b (high) | -- | -- | -- | 5.43 | 0.0% | 131k | Open | ||
gpt-oss-120b (high) | -- | -- | -- | 47.68 | 1.0% | 131k | Open | ||
gpt-oss-120b (high) | -- | -- | -- | 2.08 | 0.0% | 131k | Open | ||
gpt-oss-120b (high) Vertex | -- | -- | -- | 54.81 | 11.0% | 131k | Open | ||
gpt-oss-120b (high) | -- | -- | -- | 36.06 | 7.8% | 131k | Open | ||
gpt-oss-120b (high) | -- | -- | -- | 9.24 | 0.0% | 131k | Open | ||
gpt-oss-120b (high) | -- | -- | -- | 11.66 | 0.0% | 128k | Open | ||
gpt-oss-120b (high) | -- | -- | -- | 6.90 | 2.9% | 131k | Open | ||
gpt-oss-120b (high) | -- | -- | -- | 10.07 | 3.5% | 131k | Open | ||
gpt-oss-120b (high) (Base) | -- | -- | -- | 8.54 | 8.7% | 128k | Open | ||
gpt-oss-120b (high) | -- | -- | -- | 20.29 | 2.6% | 131k | Open | ||
NVIDIA Nemotron Nano 9B V2 | -- | -- | -- | 0.86 | 0.8% | 131k | Open | ||
Nova 2.0 Pro Preview (low) | -- | -- | -- | 6.68 | 0.0% | 256k | Proprietary | ||
Nova 2.0 Lite (medium) | -- | -- | -- | 21.65 | 0.7% | 1M | Proprietary | ||
Qwen3 Coder Next | -- | -- | -- | 1.69 | 0.0% | 128k | Open | ||
Qwen3 Coder Next (FP8) | -- | -- | -- | 1.14 | 3.3% | 262k | Open | ||
Gemma 4 12B | -- | -- | -- | 29.35 | 0.0% | 262k | Open | ||