LLM Leaderboard - Comparison of AI models from OpenAI, Anthropic, Google, Meta & others

Comparison and ranking the performance of over 250 AI models (LLMs) across key metrics including intelligence, price, performance and speed (time per task in minutes & latency as time to first answer token), context window & others.

For more details including relating to our methodology, see our FAQs.

Intelligence

Claude Fable 5.2 (max) and Claude Fable 5.2 (xhigh) are the highest intelligence models, followed by GPT-6.2 Astra (max) and Claude Fable 5.2 (high).

Time per Task

GPT-6 Luna (low) and GPT-6.1 Terra (low) have the lowest time per task, followed by GPT-6.2 Sol (low) and Gemini 4 Hydrogen (low).

Time to First Answer Token

Tiny Aya Global and Phi-4 Multimodal have the lowest time to first answer token, followed by NVIDIA Nemotron Nano 9B V2 and Nemotron 3 Nano (non-reasoning).

Cost per Task

K2 Horizon 375B A23B and Command A+ have the lowest cost per task, followed by North Mini Code and GPT-6 Luna (low).

Context Window

Llama 4 Scout and GPT-6 Sol (Daybreak Blue, max) support the largest context windows, followed by Muse Wonder (max) and Muse Wonder (high).

Further Analysis
65
$26.54
41.1
215.28
1M
62
$4.00
11.5
178.49
1M
60
$5.48
34.2
74.42
1M
59
$10.04
24.5
358.04
1M
57
$1.01
7.9
68.17
1M
55
$10.02
32.3
295.79
1M
54
$3.16
14.9
42.88
1M
51
$0.96
14.3
148.14
1M
50
$4.97
29.2
47.22
1M
MetaMuse Wonder Full Max
50
--
--
--
1M
KimiKimi K3.1 Pro
46
$3.68
38.4
157.77
1M
44
$6.95
13.3
20.17
1M
AlibabaQwen4 Max
43
$3.27
32.1
155.42
984k
36
$0.41
14.7
192.01
1M
36
$0.14
3.1
5.04
1M
35
$7.77
24.3
49.45
500k
TencentTencent Hy4
35
$1.03
13.5
117.82
1M
33
$0.60
13.2
39.36
1M
32
$5.01
22.0
69.33
1M
Thinking MachinesInkling 2 Small
31
$1.18
21.3
41.21
1M
XiaomiMiMo-V2.6-Pro
30
$0.26
34.6
42.89
1M
InclusionAILing 3.1 Flash 1019
30
$3.19
--
--
1M
MiniMaxMiniMax-M3.1-Flash
29
$0.49
17.5
50.64
1M
AlibabaQwen3.8-Flash-Next
29
$0.57
29.5
68.26
256k
StepFunStep 5 Preview
29
$2.35
13.0
21.92
1M
Joy Future AcademyJoyAI-VL-Preview
28
--
--
--
1M
28
$0.15
12.2
67.67
1M
Z AIGLM-5.3-Flash
28
$0.58
38.6
86.88
1M
XiaomiMiMo-V2.6-Flash
27
$0.13
55.5
34.30
1M
26
$2.06
19.5
70.32
1M
MetaMuse Spark Open Xhigh
25
$2.02
6.0
10.51
1M
Sapiens AIAgnes 2.5 Pro Theta
24
$0.57
22.8
8.10
1M
23
$1.77
16.9
54.34
1M
NanbeigeNanbeige4.3-33B
20
--
--
--
524k
20
$3.53
38.5
133.23
256k
China MobileJT-4.1 Flash 236B A21B
19
--
--
--
262k
MiniMaxMiniMax-M3
19
$1.29
14.4
84.94
1M
Institute of Foundation ModelsK2 Horizon 375B A23B
18
$0.00
4.6
19.32
524k
ReflectionBeam 1.0
18
$0.28
2.2
7.76
1M
UpstageSolar Pro 4
14
$0.96
71.5
32.22
512k
ApodexApodex 1.1
14
$0.76
--
--
256k
NVIDIANemotron 3.5 Super VL
14
$0.48
4.4
16.15
1M
12
$1.35
8.1
14.55
1M
NVIDIANemotron 3 Ultra 550B A55B Reasoning
12
$2.21
4.4
3.72
262k
GoogleGemini 3.5 Flash-Lite
12
$0.69
1.5
4.78
1M
SK TelecomA.X-K2
9
--
--
--
262k
LG AI ResearchK-EXAONE 2.0
8
--
--
--
262k
MetaMuse Glimmer High
6
$0.18
4.6
18.45
131k
CohereCommand A+
6
$0.00
3.5
26.75
192k
Liquid AILFM3-1.7B
6
$0.17
14.8
37.70
262k
NVIDIANemotron 3.5 Lightning
6
$0.31
3.8
15.96
1M
IBMGranite 4.2 8B
5
$0.0405
11.3
46.73
131k
5
$0.0083
4.1
40.58
128k
IBMGranite 4.2 3B
5
--
--
--
131k
MistralMistral Medium 3.5
5
$1.04
4.5
25.20
256k
4
--
--
78.93
256k
4
$0.0399
1.7
15.61
256k
4
$0.35
6.5
11.78
131k
CohereNorth Mini Code
3
$0.00
2.8
4.70
256k
NVIDIANVIDIA Nemotron 3 Nano 4B
2
--
--
--
262k
Liquid AILFM3-VL-2B
2
$0.12
1.7
13.28
128k
China MobileJT-35B-Flash
--
--
--
--
256k
AlibabaQwen3.5 Omni Plus
--
--
--
2.72
256k
--
--
--
--
1M
--
--
--
4.52
262k
--
--
--
--
262k
GoogleGemma 3 270M
--
--
--
--
32k
--
--
--
--
262k
AlibabaQwen3 Omni 30B A3B Instruct
--
--
--
1.15
66k
--
--
--
16.75
256k
--
--
--
36.52
262k
IBMGranite 4.2 30B
--
--
--
--
131k
Institute of Foundation ModelsK2 Horizon 7B
--
--
--
--
524k
--
--
--
1.30
131k
OpenAIo3
--
--
--
5.40
200k
IBMGranite 4.0 Micro
--
--
--
--
128k
--
--
--
1.07
262k
--
--
--
--
128k
--
--
--
0.86
1M
AlibabaQwen3 Next 80B A3B Instruct
--
--
--
1.20
262k
MicrosoftPhi-4 Multimodal Instruct
--
--
--
0.50
128k
--
--
--
1.13
131k
AI9StarsG9v3-3B
--
--
--
--
131k
--
--
--
1.50
262k
Institute of Foundation ModelsK2 Horizon 3.7B
--
--
--
--
524k
Allen Institute for AIOlmo 3 7B Think
--
--
--
--
66k
NaverHyperCLOVA X SEED Think (32B)
--
--
--
--
128k
Multiverse ComputingHyperNova 60B 2605 High, Based on gpt-oss-120b
--
--
--
--
131k
AmazonNova Micro
--
--
--
1.25
130k
--
--
--
--
262k
Prime IntellectINTELLECT-3 Based on GLM-4.5-Air
--
--
--
--
131k
Allen Institute for AIOlmo 3.1 32B Think
--
--
--
--
66k
Nex AGINex-N2-Pro Based on Qwen3.5-397B-A17B
--
--
--
--
262k
Liquid AILFM2.5-VL-1.6B
--
--
--
--
32k
China MobileJT-MINI
--
--
--
--
128k
Allen Institute for AIMolmo2-8B
--
--
--
--
37k
--
--
--
--
262k
InclusionAILing-3.0-flash-VL
--
--
--
--
262k
OpenBMBMiniCPM-V 4.6 1.3B
--
--
--
--
262k
SarvamSarvam 105B High
--
--
--
9.73
128k
MetaLlama 3.1 Instruct 405B
--
--
--
--
128k
InclusionAIRing-flash-2.0
--
--
--
--
128k
Liquid AILFM2.5-1.2B-Instruct
--
--
--
--
32k
Swiss AI InitiativeApertus 70B Instruct
--
--
--
--
66k
ByteDance SeedDoubao Seed Code
--
--
--
--
256k
Institute of Foundation ModelsK2 Horizon MoVA 36B A4B
--
--
--
--
524k
IBMGranite 4.0 350M
--
--
--
--
33k
OpenAIAstra for Law 6.2 Max
--
--
--
--
1M
KimiKimi Linear 48B A3B Instruct
--
--
--
--
1M
UpstageSolar Open 100B Reasoning
--
--
--
--
128k
OpenAIGPT-5.3 Codex Xhigh
--
--
--
37.31
400k
Liquid AILFM2.5-1.2B-Thinking
--
--
--
--
32k
LongCatLongCat 2.0
--
--
--
51.59
1M
Trillion LabsTri-21B-Think
--
--
--
--
32k
IBMGranite 4.0 H Small
--
--
--
--
128k
MetaLlama 3.2 Instruct 11B (Vision)
--
--
--
5.30
128k
LongCatLongCat Flash Lite
--
--
--
--
256k
NVIDIANemotron 3.5 Bolt E4B 4GB Reasoning
--
--
--
--
131k
--
--
--
25.49
1M
UpstageSolar Mini 4
--
--
--
32.21
1M
OpenBMBMiniCPM5-2B
--
--
--
--
131k
Motif TechnologiesMotif-2-12.7B-Reasoning
--
--
--
--
128k
--
--
--
3.21
262k
MistralMinistral 3 3B
--
--
--
1.75
256k
InclusionAILing-3.0-flash-Fin
--
--
--
--
262k
--
--
--
31.56
256k
--
--
--
--
128k
AlibabaQwen3.5 Omni Flash
--
--
--
2.88
256k
MistralMagistral Small 1.2
--
--
--
3.06
128k
MistralMinistral 3 14B
--
--
--
2.36
256k
--
--
--
--
128k
SarvamSarvam 30B High
--
--
--
--
66k
InceptionMercury 2.5
--
--
--
2.32
260k
DeepSeekDeepSeek V4 Flash Vision Max
--
--
--
41.62
1M
--
--
--
--
128k
AI21 LabsJamba 1.7 Large
--
--
--
--
256k
NVIDIANemotron 3.5 Bolt 74B-A9B
--
--
--
--
262k
NanbeigeNanbeige4.1-3B
--
--
--
--
256k
UpstageSolar Open2 250B
--
--
--
--
1M
InclusionAILing 3.0 Tiny
--
--
--
15.06
262k
CelerisCeleris-1
--
--
--
1.29
131k
CohereTiny Aya Global
--
--
--
0.18
8k
--
--
--
--
64k
--
--
--
24.62
128k
MistralMagistral Medium 1.2
--
--
--
--
128k
Swiss AI InitiativeApertus 8B Instruct
--
--
--
--
66k
NVIDIANemotron 3 Nano Omni 30B A3B Reasoning
--
--
--
--
256k
KimiKimi K2.7 Code
--
--
--
35.25
256k
AlibabaQwen3.8 2.4T A95B
--
--
--
118.21
262k
Allen Institute for AIOlmo 3 7B Instruct
--
--
--
--
66k
MetaLlama 4 Maverick
--
--
--
1.28
1M
OpenAIGPT-6 Sol Daybreak Blue, max
--
--
--
--
1M
Allen Institute for AIOlmo 3.1 32B Instruct
--
--
--
--
66k
MistralMinistral 3 8B
--
--
--
1.93
256k
MetaLlama 3.3 Instruct 70B
--
--
--
2.16
128k
NVIDIANemotron Cascade 2 30B A3B
--
--
--
--
1M
PerplexityR1 1776
--
--
--
--
128k
MetaLlama 3.2 Instruct 90B (Vision)
--
--
--
--
128k
Institute of Foundation ModelsK2 Horizon 0.9B
--
--
--
--
131k
MicrosoftPhi-4 Mini Instruct
--
--
--
4.61
128k
GoogleGemini 3 Deep Think
--
--
--
--
128k
BaiduERNIE 5.0 Thinking Preview
--
--
--
--
128k
IBMGranite 4.0 H 350M
--
--
--
--
33k
ServiceNowApriel-v1.6-15B-Thinker
--
--
--
--
128k
AlibabaQwen3.7 Plus
--
--
--
45.66
1M
Nous ResearchDeepHermes 3 - Mistral 24B Preview Non-reasoning
--
--
--
--
32k
StepFunStep3 VL 10B
--
--
--
--
66k
MetaLlama 4 Scout
--
--
--
1.12
10M
BaiduERNIE 4.5 300B A47B
--
--
--
--
131k
Allen Institute for AIMolmo 7B-D
--
--
--
--
4k
Motif TechnologiesMotif 3
--
--
--
--
262k
AI21 LabsJamba 1.7 Mini
--
--
--
--
258k
Arcee AITrinity Large Thinking
--
--
--
--
512k
Nous ResearchDeepHermes 3 - Llama-3.1 8B Preview Non-reasoning
--
--
--
--
128k
AlibabaQwen3 Omni 30B A3B (Reasoning)
--
--
--
28.36
66k
GoogleGemini 3.1 Pro Preview
--
--
--
15.49
1M
AI9StarsG9v3-39A5B
--
--
--
--
131k
GoogleDiffusionGemma 26B A4B
--
--
--
--
256k
OpenAIGPT-5.5 Instant (June 2026)
--
--
--
1.77
400k
TII UAEFalcon-H1R-7B
--
--
--
--
256k
AlibabaQwen3 Next 80B A3B (Reasoning)
--
--
--
--
262k
NVIDIALlama 3.1 Nemotron Ultra 253B v1 Reasoning
--
--
--
--
128k
IBMGranite 4.0 H 1B
--
--
--
--
128k
Reka AIReka Flash 3
--
--
--
8.10
128k
Korea TelecomMi:dm K 2.5 Pro
--
--
--
--
128k
Liquid AILFM2.5-2.6B
--
--
--
--
128k
Liquid AILFM2.5-8B-A1B
--
--
--
--
33k
OpenAIGPT-5.5 Pro Xhigh
--
--
--
--
922k
AmazonNova Premier
--
--
--
--
1M
Deep CogitoCogito v2.1 Reasoning
--
--
--
--
128k
InclusionAIRing-2.6-1T
--
--
--
--
262k
MicrosoftPhi-4
--
--
--
3.49
16k
Sapiens AIAgnes 2.5 Pro Beta
--
--
--
--
1M
AI21 LabsJamba Reasoning 3B
--
--
--
--
262k
Multiverse ComputingQuasar 438B Max, Based on GLM-5.2
--
--
--
--
1M
Liquid AILFM2 24B A2B
--
--
--
--
33k
KwaiKATKAT Coder Pro V2
--
--
--
--
256k
AlibabaQwen3 Coder Next
--
--
--
1.54
256k

Key definitions

Frequently Asked Questions