All evaluations
Artificial Analysis Openness Index
A composite measure providing an industry standard to communicate model openness for users and developers.
The Artificial Analysis Openness Index assesses how 'open' models are on the basis of their availability and transparency across different components (e.g. models weights, training data, and model architecture).
Availability represents the ability to use a model via API, self-hosting through open weights, and use freely with permissive licensing. Transparency captures the degree to which a model's methodology and data have been disclosed, shared, and permissively licensed for the community to use to understand a model's inputs and replicate or build on its approach.
All evaluations are conducted independently by Artificial Analysis. More information can be found on our Intelligence Benchmarking Methodology page.
Openness Index
Olmo 3.1 32B Instruct scores the highest on Openness Index with a score of 89, followed by Molmo 7B-D with a score of 89, and Olmo 3 7B Instruct with a score of 89
Openness Index
o3 scores the lowest on Openness Index with a score of 6, followed by Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) with a score of 6, and Gemini 2.5 Pro with a score of 6
Artificial Analysis Openness Index: Results
Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open)
Reasoning models are indicated by a lightbulb icon
Artificial Analysis Openness Index: Components
Openness Index underlying score contribution by components, up to a maximum of 18 (higher is more open)
Reasoning models are indicated by a lightbulb icon
Artificial Analysis Openness Index: Model Availability vs. Model Transparency
Model availability reflects the availability of a model for usage and associated license (maximum 6 points) · Model transparency reflects methodology and data disclosures, data sharing, and code and licensing associated with a model's training process (maximum 12 points)
Most attractive quadrant
Alibaba
Allen Institute for AI
Anthropic
DeepSeek
Google
Kimi
MBZUAI Institute of Foundation Models
MiniMax
Mistral
NVIDIA
OpenAI
Xiaomi
Z AI
Artificial Analysis Openness Index: Score vs. Release Date
Artificial Analysis Openness Index · Release date
Most attractive region
Alibaba
Allen Institute for AI
Anthropic
DeepSeek
Google
Kimi
MBZUAI Institute of Foundation Models
MiniMax
Mistral
NVIDIA
OpenAI
Xiaomi
Z AI
Artificial Analysis Openness Index vs. Artificial Analysis Intelligence Index
Artificial Analysis Openness Index · Artificial Analysis Intelligence Index
Most attractive quadrant
Alibaba
Allen Institute for AI
Anthropic
DeepSeek
Google
Kimi
MBZUAI Institute of Foundation Models
MiniMax
Mistral
NVIDIA
OpenAI
Xiaomi
Z AI
Openness Index Composition
Dimension
Component
Scoring
1. Model availability
Weights
Access
0Closed weights, no API
1Closed weights, API limits token visibility
2Closed weights, API available
3Open weights
License
0Closed weights or no commercial use
1Commercial use, attribution required
2Commercial use, no attribution required
3Commercial use, no attribution required, no meaningful limitations
2. Model transparency
Data:Pre & Post Training(score represents average across each)
Access
0No or limited disclosure
1Partial data source detail and categorization disclosed
2Full data mix disclosure, substantial data shared¹
3Full data shared
License (most restrictive)
0No commercial use/no substantial data shared
1Commercial use, attribution required
2Commercial use, no attribution required
3Commercial use, no attribution required, no meaningful limitations
Methodology
Disclosure
0No or limited disclosure
1Model architecture disclosure
2Limited general technical disclosure
3Full technical details disclosed
License (most restrictive)
0No code disclosed/released
1Frameworks disclosed, openly available for commercial use
2End-to-end training pipeline code or guide released
3End-to-end training pipeline code or guide released, and commercial use allowed
Scoring methodology
Each component is scored on a 0-3 qualitative scale based on the best-fitting openness 'archetype', with each model assessed based on the full set of public first-party information available.
We synthesize these underlying factors into a unified metric, the Artificial Analysis Openness Index, as follows:
- Data elements are averaged between pre- and post-training (to give a total of 6 possible points across data)
- All component scores are added (up to a maximum of 18/18 points)
- This score is normalized to a 0-100 scale
Where models are derived from a third-party base model, they may be constrained by the licensing or limited disclosure of the upstream model. For incremental/update releases, we only consider disclosures explicitly about the new release (including allowing model creators to declare which components remain consistent with an earlier release).
Openness Index Leaderboard
| 1 |  Allen Institute for AI | Olmo 3.1 32B Instruct | 88.89 | 12.16 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 2 | Allen Institute for AI | Molmo 7B-D | 88.89 | 9.25 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 3 | Allen Institute for AI | Olmo 3 7B Instruct | 88.89 | 8.15 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 4 | Allen Institute for AI | Olmo 3.1 32B Think | 88.89 | 13.94 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 5 | Allen Institute for AI | Olmo 3 7B Think | 88.89 | 9.43 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 6 |  MBZUAI Institute of Foundation Models | K2 Think V2 | 88.89 | 24.12 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 7 | MBZUAI Institute of Foundation Models | K2-V2 (low) | 88.89 | 14.44 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 8 | MBZUAI Institute of Foundation Models | K2-V2 (high) | 88.89 | 20.61 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 9 | MBZUAI Institute of Foundation Models | K2-V2 (medium) | 88.89 | 18.68 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 10 |  Swiss AI Initiative | Apertus 70B Instruct | 88.89 | 7.70 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 11 | Swiss AI Initiative | Apertus 8B Instruct | 88.89 | 5.88 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 12 | Allen Institute for AI | OLMo 2 7B | 88.89 | 9.30 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 13 | Allen Institute for AI | Olmo 3 32B Think | 88.89 | 12.09 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 14 | Allen Institute for AI | OLMo 2 32B | 88.89 | 10.57 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 15 |  NVIDIA | NVIDIA Nemotron 3 Super 120B A12B (Reasoning) | 83.33 | 35.97 | 6.00 | 9.00 | 2.00 | 1.00 | 2.00 | 1.00 |
| 16 | NVIDIA | NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) | 83.33 | 24.27 | 6.00 | 9.00 | 2.00 | 1.00 | 2.00 | 1.00 |
| 17 | NVIDIA | NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | 72.22 | 13.16 | 6.00 | 7.00 | 2.00 | 1.00 | 2.00 | 1.00 |
| 18 | NVIDIA | NVIDIA Nemotron Nano 12B v2 VL (Reasoning) | 72.22 | 14.89 | 6.00 | 7.00 | 2.00 | 1.00 | 2.00 | 1.00 |
| 19 | NVIDIA | NVIDIA Nemotron Nano 9B V2 (Reasoning) | 72.22 | 14.76 | 6.00 | 7.00 | 2.00 | 1.00 | 2.00 | 1.00 |
| 20 | NVIDIA | NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) | 72.22 | 10.09 | 6.00 | 7.00 | 2.00 | 1.00 | 2.00 | 1.00 |
| 21 | Allen Institute for AI | Molmo2-8B | 72.22 | 7.30 | 6.00 | 7.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 22 |  Kimi | Kimi Linear 48B A3B Instruct | 61.11 | 14.41 | 6.00 | 5.00 | 1.00 | 0.00 | 1.00 | 0.00 |
| 23 |  IBM | Granite 4.1 3B | 61.11 | 8.54 | 6.00 | 5.00 | 2.00 | 1.00 | 2.00 | 1.00 |
| 24 | IBM | Granite 4.1 30B | 61.11 | 14.69 | 6.00 | 5.00 | 2.00 | 1.00 | 2.00 | 1.00 |
| 25 | IBM | Granite 4.1 8B | 61.11 | 12.38 | 6.00 | 5.00 | 2.00 | 1.00 | 2.00 | 1.00 |
| 26 | IBM | Granite 4.0 H 350M | 55.56 | 5.44 | 6.00 | 4.00 | 2.00 | 1.00 | 2.00 | 1.00 |
| 27 | IBM | Granite 4.0 H 1B | 55.56 | 7.99 | 6.00 | 4.00 | 2.00 | 1.00 | 2.00 | 1.00 |
| 28 | IBM | Granite 4.0 1B | 55.56 | 7.34 | 6.00 | 4.00 | 2.00 | 1.00 | 2.00 | 1.00 |
| 29 | IBM | Granite 4.0 H Small | 55.56 | 10.81 | 6.00 | 4.00 | 2.00 | 1.00 | 2.00 | 1.00 |
| 30 | IBM | Granite 4.0 Micro | 55.56 | 7.67 | 6.00 | 4.00 | 2.00 | 1.00 | 2.00 | 1.00 |
| 31 | IBM | Granite 4.0 350M | 55.56 | 6.10 | 6.00 | 4.00 | 2.00 | 1.00 | 2.00 | 1.00 |
| 32 |  Baidu | ERNIE 4.5 300B A47B | 55.56 | 14.96 | 6.00 | 4.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 33 |  Z AI | GLM-4.5 (Reasoning) | 55.56 | 26.42 | 6.00 | 4.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 34 | Z AI | GLM-4.5-Air | 55.56 | 23.17 | 6.00 | 4.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 35 | NVIDIA | Llama Nemotron Super 49B v1.5 (Non-reasoning) | 52.78 | 14.59 | 4.00 | 5.50 | 1.00 | 0.00 | 1.00 | 1.00 |
| 36 | NVIDIA | Llama 3.3 Nemotron Super 49B v1 (Reasoning) | 52.78 | 18.49 | 4.00 | 5.50 | 1.00 | 0.00 | 1.00 | 1.00 |
| 37 | NVIDIA | Llama Nemotron Super 49B v1.5 (Reasoning) | 52.78 | 18.68 | 4.00 | 5.50 | 1.00 | 0.00 | 1.00 | 1.00 |
| 38 | NVIDIA | Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) | 52.78 | 15.02 | 4.00 | 5.50 | 1.00 | 0.00 | 1.00 | 1.00 |
| 39 | NVIDIA | Llama 3.3 Nemotron Super 49B v1 (Non-reasoning) | 52.78 | 14.35 | 4.00 | 5.50 | 1.00 | 0.00 | 1.00 | 1.00 |
| 40 | NVIDIA | Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning) | 52.78 | 14.43 | 4.00 | 5.50 | 1.00 | 0.00 | 1.00 | 1.00 |
| 41 |  Xiaomi | MiMo-V2-Flash (Reasoning) | 52.78 | 39.24 | 6.00 | 3.50 | 0.00 | 0.00 | 1.00 | 0.00 |
| 42 | Z AI | GLM-4.5V (Reasoning) | 52.78 | 15.09 | 6.00 | 3.50 | 1.00 | 0.00 | 0.00 | 0.00 |
| 43 | Z AI | GLM-4.5V (Non-reasoning) | 52.78 | 12.74 | 6.00 | 3.50 | 1.00 | 0.00 | 0.00 | 0.00 |
| 44 |  Mistral | Magistral Small 1.2 | 50.00 | 18.16 | 6.00 | 3.00 | 0.00 | 0.00 | 1.00 | 1.00 |
| 45 |  DeepSeek | DeepSeek R1 0528 (May '25) | 50.00 | 27.07 | 6.00 | 3.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 46 | DeepSeek | DeepSeek V4 Flash (Reasoning, Max Effort) | 50.00 | 46.52 | 6.00 | 3.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 47 | DeepSeek | DeepSeek V4 Pro (Reasoning, High Effort) | 50.00 | 49.79 | 6.00 | 3.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 48 | DeepSeek | DeepSeek V4 Pro (Reasoning, Max Effort) | 50.00 | 51.51 | 6.00 | 3.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 49 | DeepSeek | DeepSeek V4 Flash (Reasoning, High Effort) | 50.00 | 44.87 | 6.00 | 3.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 50 |  Microsoft | Phi-4 | 50.00 | 10.41 | 6.00 | 3.00 | 1.00 | 0.00 | 1.00 | 0.00 |
| 51 | Microsoft | Phi-4 Multimodal Instruct | 50.00 | 10.04 | 6.00 | 3.00 | 1.00 | 0.00 | 1.00 | 0.00 |
| 52 | Microsoft | Phi-4 Mini Instruct | 50.00 | 8.39 | 6.00 | 3.00 | 1.00 | 0.00 | 1.00 | 0.00 |
| 53 | Z AI | GLM-5 (Reasoning) | 50.00 | 49.77 | 6.00 | 3.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 54 |  Google | Gemma 3 1B Instruct | 50.00 | 5.55 | 6.00 | 3.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 55 | Google | Gemma 3 4B Instruct | 50.00 | 6.30 | 6.00 | 3.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 56 | Google | Gemma 3 27B Instruct | 50.00 | 10.31 | 6.00 | 3.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 57 | Google | Gemma 3 12B Instruct | 50.00 | 8.79 | 6.00 | 3.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 58 | Google | Gemma 3n E2B Instruct | 50.00 | 4.76 | 6.00 | 3.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 59 | Google | Gemma 3n E4B Instruct | 50.00 | 6.38 | 6.00 | 3.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 60 |  StepFun | Step 3.5 Flash | 50.00 | 37.80 | 6.00 | 3.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 61 |  Alibaba | Qwen3 VL 32B Instruct | 50.00 | 17.19 | 6.00 | 3.00 | 1.00 | 0.00 | 1.00 | 0.00 |
| 62 | Alibaba | Qwen3 VL 235B A22B Instruct | 50.00 | 20.75 | 6.00 | 3.00 | 1.00 | 0.00 | 1.00 | 0.00 |
| 63 | Alibaba | Qwen3 VL 30B A3B Instruct | 50.00 | 16.05 | 6.00 | 3.00 | 1.00 | 0.00 | 1.00 | 0.00 |
| 64 | Alibaba | Qwen3 VL 30B A3B (Reasoning) | 50.00 | 19.68 | 6.00 | 3.00 | 1.00 | 0.00 | 1.00 | 0.00 |
| 65 | Alibaba | Qwen3 VL 235B A22B (Reasoning) | 50.00 | 27.64 | 6.00 | 3.00 | 1.00 | 0.00 | 1.00 | 0.00 |
| 66 | Alibaba | Qwen3 VL 4B (Reasoning) | 50.00 | 13.73 | 6.00 | 3.00 | 1.00 | 0.00 | 1.00 | 0.00 |
| 67 | Alibaba | Qwen3 VL 4B Instruct | 50.00 | 9.55 | 6.00 | 3.00 | 1.00 | 0.00 | 1.00 | 0.00 |
| 68 | Alibaba | Qwen3 VL 8B (Reasoning) | 50.00 | 16.66 | 6.00 | 3.00 | 1.00 | 0.00 | 1.00 | 0.00 |
| 69 | Alibaba | Qwen3 VL 8B Instruct | 50.00 | 14.30 | 6.00 | 3.00 | 1.00 | 0.00 | 1.00 | 0.00 |
| 70 | Alibaba | Qwen3 VL 32B (Reasoning) | 50.00 | 24.72 | 6.00 | 3.00 | 1.00 | 0.00 | 1.00 | 0.00 |
| 71 |  Nous Research | Hermes 4 - Llama-3.1 70B (Non-reasoning) | 47.22 | 12.63 | 4.00 | 4.50 | 1.00 | 0.00 | 2.00 | 0.00 |
| 72 | Nous Research | Hermes 4 - Llama-3.1 405B (Reasoning) | 47.22 | 18.56 | 4.00 | 4.50 | 1.00 | 0.00 | 2.00 | 0.00 |
| 73 | Nous Research | Hermes 4 - Llama-3.1 405B (Non-reasoning) | 47.22 | 17.63 | 4.00 | 4.50 | 1.00 | 0.00 | 2.00 | 0.00 |
| 74 | Nous Research | Hermes 4 - Llama-3.1 70B (Reasoning) | 47.22 | 15.99 | 4.00 | 4.50 | 1.00 | 0.00 | 2.00 | 0.00 |
| 75 | DeepSeek | DeepSeek R1 0528 Qwen3 8B | 47.22 | 16.43 | 6.00 | 2.50 | 0.00 | 0.00 | 1.00 | 0.00 |
| 76 |  ServiceNow | Apriel-v1.5-15B-Thinker | 47.22 | 28.33 | 6.00 | 2.50 | 0.00 | 0.00 | 1.00 | 0.00 |
| 77 | Google | Gemma 3 270M | 44.44 | 7.71 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 78 |  TII UAE | Falcon-H1R-7B | 44.44 | 15.80 | 4.00 | 4.00 | 1.00 | 0.00 | 1.00 | 0.00 |
| 79 | NVIDIA | Llama 3.1 Nemotron Instruct 70B | 44.44 | 13.44 | 4.00 | 4.00 | 0.00 | 0.00 | 1.00 | 1.00 |
| 80 |  LongCat | LongCat Flash Lite | 44.44 | 23.93 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 81 |  OpenBMB | MiniCPM-V 4.6 1.3B | 44.44 | 12.65 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 82 |  Arcee AI | Trinity Large Thinking | 44.44 | 31.87 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 83 | Z AI | GLM-5.1 (Reasoning) | 44.44 | 51.41 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 84 | Alibaba | Qwen3 Next 80B A3B (Reasoning) | 44.44 | 26.72 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 85 | Alibaba | Qwen3 Omni 30B A3B (Reasoning) | 44.44 | 15.62 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 86 | Alibaba | Qwen3 Next 80B A3B Instruct | 44.44 | 20.11 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 87 | Alibaba | Qwen3 Omni 30B A3B Instruct | 44.44 | 10.68 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 88 |  InclusionAI | Ling-flash-2.0 | 44.44 | 15.74 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 89 | InclusionAI | Ling-1T | 44.44 | 19.04 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 90 | InclusionAI | Ling-mini-2.0 | 44.44 | 9.19 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 91 | Mistral | Devstral Small (Jul '25) | 44.44 | 15.21 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 92 | DeepSeek | DeepSeek V3.2 Exp (Non-reasoning) | 44.44 | 28.44 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 93 | DeepSeek | DeepSeek V3.2 Exp (Reasoning) | 44.44 | 32.94 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 94 | Kimi | Kimi K2 | 44.44 | 26.32 | 4.00 | 4.00 | 1.00 | 0.00 | 1.00 | 0.00 |
| 95 | Z AI | GLM-4.7 (Non-reasoning) | 44.44 | 34.16 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 96 | Z AI | GLM-4.7-Flash (Non-reasoning) | 44.44 | 22.07 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 97 | Z AI | GLM-4.7 (Reasoning) | 44.44 | 42.11 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 98 | Z AI | GLM-4.6 (Reasoning) | 44.44 | 32.51 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 99 | Z AI | GLM-4.6 (Non-reasoning) | 44.44 | 30.24 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 100 | Z AI | GLM-4.7-Flash (Reasoning) | 44.44 | 30.15 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 101 | Alibaba | Qwen3 235B A22B 2507 (Reasoning) | 44.44 | 29.54 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 102 | Alibaba | Qwen3 235B A22B 2507 Instruct | 44.44 | 24.96 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 103 | Alibaba | Qwen3 Coder 480B A35B Instruct | 44.44 | 24.77 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 104 | Alibaba | Qwen3 Coder 30B A3B Instruct | 44.44 | 19.98 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 105 | Alibaba | Qwen3 30B A3B 2507 Instruct | 44.44 | 15.00 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 106 | Alibaba | Qwen3 30B A3B 2507 (Reasoning) | 44.44 | 22.41 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 107 | Alibaba | Qwen3 4B 2507 (Reasoning) | 44.44 | 18.18 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 108 | Alibaba | Qwen3 4B 2507 Instruct | 44.44 | 12.88 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 109 |  ByteDance Seed | Seed-OSS-36B-Instruct | 44.44 | 25.16 | 6.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 110 | Alibaba | Qwen3 Coder Next | 41.67 | 28.28 | 6.00 | 1.50 | 0.00 | 0.00 | 1.00 | 0.00 |
| 111 |  OpenAI | gpt-oss-120B (high) | 38.89 | 33.27 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 112 | OpenAI | gpt-oss-20B (high) | 38.89 | 24.47 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 113 |  Meta | Llama 3.3 Instruct 70B | 38.89 | 14.49 | 4.00 | 3.00 | 1.00 | 0.00 | 1.00 | 0.00 |
| 114 | Meta | Llama 3.1 Instruct 405B | 38.89 | 17.38 | 4.00 | 3.00 | 1.00 | 0.00 | 1.00 | 0.00 |
| 115 | Meta | Llama 3.2 Instruct 90B (Vision) | 38.89 | 11.90 | 4.00 | 3.00 | 1.00 | 0.00 | 1.00 | 0.00 |
| 116 | Meta | Llama 3.2 Instruct 11B (Vision) | 38.89 | 8.73 | 4.00 | 3.00 | 1.00 | 0.00 | 1.00 | 0.00 |
| 117 | Google | Gemma 4 31B (Reasoning) | 38.89 | 39.18 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 118 | Google | Gemma 4 26B A4B (Reasoning) | 38.89 | 31.21 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 119 | Google | Gemma 4 E2B (Reasoning) | 38.89 | 15.21 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 120 | Google | Gemma 4 E4B (Reasoning) | 38.89 | 18.76 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 121 | Mistral | Mistral Large 3 | 38.89 | 22.80 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 122 | Mistral | Mistral Small 4 (Non-reasoning) | 38.89 | 18.62 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 123 | Mistral | Mistral Small 4 (Reasoning) | 38.89 | 27.80 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 124 |  Perplexity | R1 1776 | 38.89 | 11.99 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 125 |  Reka AI | Reka Flash 3 | 38.89 | 9.52 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 126 | Nous Research | DeepHermes 3 - Mistral 24B Preview (Non-reasoning) | 38.89 | 10.89 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 127 | Xiaomi | MiMo-V2.5 | 38.89 | 49.03 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 128 | Xiaomi | MiMo-V2.5-Pro | 38.89 | 53.83 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 129 |  Sarvam | Sarvam 105B (high) | 38.89 | 18.16 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 130 | Sarvam | Sarvam 30B (high) | 38.89 | 12.34 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 131 |  Deep Cogito | Cogito v2.1 (Reasoning) | 38.89 | - | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 132 |  AI21 Labs | Jamba Reasoning 3B | 38.89 | 9.60 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 133 | Alibaba | Qwen3.5 122B A10B (Reasoning) | 38.89 | 41.60 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 134 | Alibaba | Qwen3.5 9B (Non-reasoning) | 38.89 | 27.33 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 135 | Alibaba | Qwen3.5 397B A17B (Reasoning) | 38.89 | 45.05 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 136 | Alibaba | Qwen3.6 27B (Reasoning) | 38.89 | 45.82 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 137 | Alibaba | Qwen3.5 9B (Reasoning) | 38.89 | 32.43 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 138 | Alibaba | Qwen3.5 2B (Non-reasoning) | 38.89 | 14.67 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 139 | Alibaba | Qwen3.6 35B A3B (Reasoning) | 38.89 | 43.49 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 140 | Alibaba | Qwen3.5 122B A10B (Non-reasoning) | 38.89 | 35.87 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 141 | Alibaba | Qwen3.5 397B A17B (Non-reasoning) | 38.89 | 40.10 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 142 | Alibaba | Qwen3.5 0.8B (Reasoning) | 38.89 | 10.52 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 143 | Alibaba | Qwen3.5 4B (Reasoning) | 38.89 | 27.08 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 144 | Alibaba | Qwen3.5 2B (Reasoning) | 38.89 | 16.29 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 145 | Alibaba | Qwen3.5 0.8B (Non-reasoning) | 38.89 | 9.91 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 146 | Alibaba | Qwen3.5 4B (Non-reasoning) | 38.89 | 22.60 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 147 | Alibaba | Qwen3.5 35B A3B (Non-reasoning) | 38.89 | 30.69 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 148 | InclusionAI | Ling 2.6 Flash | 38.89 | 26.16 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 149 | InclusionAI | Ring-1T | 38.89 | 22.78 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 150 | InclusionAI | Ling-2.6-1T | 38.89 | 33.61 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 151 | InclusionAI | Ring-flash-2.0 | 38.89 | 14.02 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 152 | Mistral | Mistral Small 3.2 | 38.89 | 15.07 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 153 | DeepSeek | DeepSeek V3.1 Terminus (Non-reasoning) | 38.89 | 28.52 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 154 | DeepSeek | DeepSeek V3.1 Terminus (Reasoning) | 38.89 | 33.93 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 155 | Alibaba | Qwen3.5 35B A3B (Reasoning) | 38.89 | 37.12 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 156 | Alibaba | Qwen3.5 27B (Reasoning) | 38.89 | 42.07 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 157 | Alibaba | Qwen3.5 27B (Non-reasoning) | 38.89 | 37.18 | 6.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 158 | DeepSeek | DeepSeek R1 Distill Llama 70B | 36.11 | 15.95 | 4.00 | 2.50 | 0.00 | 0.00 | 1.00 | 0.00 |
| 159 | Mistral | Mistral Medium 3.5 | 33.33 | 39.23 | 5.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 160 |  Liquid AI | LFM2 2.6B | 33.33 | 8.04 | 4.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 161 | Liquid AI | LFM2 8B A1B | 33.33 | 7.03 | 4.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 162 | Kimi | Kimi K2.6 | 33.33 | 53.90 | 4.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 163 | Nous Research | DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning) | 33.33 | 7.58 | 5.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 164 |  Tencent | Hy3-preview (Reasoning) | 33.33 | 41.85 | 5.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 165 | Tencent | Hy3-preview (Non-reasoning) | 33.33 | 33.66 | 5.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 166 |  Cohere | Command A | 33.33 | 13.48 | 3.00 | 3.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 167 | Liquid AI | LFM2 1.2B | 33.33 | 6.33 | 4.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 168 | Kimi | Kimi K2.5 (Reasoning) | 33.33 | 46.81 | 4.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 169 |  Naver | HyperCLOVA X SEED Think (32B) | 30.56 | 23.72 | 4.00 | 1.50 | 1.00 | 0.00 | 0.00 | 0.00 |
| 170 | Meta | Llama 4 Scout | 27.78 | 13.52 | 4.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 171 | Meta | Llama 4 Maverick | 27.78 | 18.36 | 4.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 172 | Mistral | Magistral Medium 1.2 | 27.78 | 27.10 | 2.00 | 3.00 | 0.00 | 0.00 | 1.00 | 1.00 |
| 173 | Liquid AI | LFM2.5-1.2B-Thinking | 27.78 | 8.08 | 4.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 174 | Liquid AI | LFM2.5-1.2B-Instruct | 27.78 | 8.04 | 4.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 175 | Liquid AI | LFM2 24B A2B | 27.78 | 10.49 | 4.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 176 | Liquid AI | LFM2.5-VL-1.6B | 27.78 | 6.18 | 4.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 177 |  LG AI Research | Exaone 4.0 1.2B (Non-reasoning) | 27.78 | 8.11 | 3.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 178 | LG AI Research | Exaone 4.0 1.2B (Reasoning) | 27.78 | 8.26 | 3.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 179 | LG AI Research | K-EXAONE (Reasoning) | 27.78 | 32.12 | 4.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 180 | LG AI Research | EXAONE 4.0 32B (Reasoning) | 27.78 | 16.68 | 3.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 181 | LG AI Research | EXAONE 4.0 32B (Non-reasoning) | 27.78 | 11.66 | 3.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 182 |  MiniMax | MiniMax-M2.1 | 27.78 | 39.42 | 4.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 183 | MiniMax | MiniMax-M2.5 | 27.78 | 41.93 | 4.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 184 | MiniMax | MiniMax-M2 | 27.78 | 36.09 | 4.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 185 | Kimi | Kimi K2 0905 | 27.78 | 30.85 | 4.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 186 | Kimi | Kimi K2 Thinking | 27.78 | 40.89 | 4.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 187 | MiniMax | MiniMax-M2.7 | 22.22 | 49.62 | 3.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 188 | AI21 Labs | Jamba 1.7 Mini | 22.22 | 8.07 | 4.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 189 | AI21 Labs | Jamba 1.7 Large | 22.22 | 10.88 | 4.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 190 | Alibaba | Qwen3 Max | 16.67 | 31.38 | 2.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 191 | Alibaba | Qwen3 Max Thinking (Preview) | 16.67 | 32.48 | 2.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 192 | Google | Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) | 11.11 | 19.42 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 193 |  Anthropic | Claude 4.5 Haiku (Non-reasoning) | 11.11 | 31.05 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 194 | Anthropic | Claude 4.5 Haiku (Reasoning) | 11.11 | 37.09 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 195 |  xAI | Grok 3 mini Reasoning (high) | 11.11 | 32.08 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 196 | xAI | Grok 4.1 Fast (Non-reasoning) | 11.11 | 23.56 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 197 |  Amazon | Nova Micro | 11.11 | 10.27 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 198 | Amazon | Nova Premier | 11.11 | 19.01 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 199 |  Upstage | Solar Pro 2 (Reasoning) | 11.11 | 14.92 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 200 | Upstage | Solar Pro 2 (Non-reasoning) | 11.11 | 13.59 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 201 | ByteDance Seed | Doubao Seed Code | 11.11 | 33.52 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 202 | OpenAI | GPT-5.1 (Non-reasoning) | 11.11 | 27.42 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 203 | OpenAI | GPT-5 (ChatGPT) | 11.11 | 21.83 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 204 | Google | Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) | 11.11 | 25.70 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 205 | Anthropic | Claude Opus 4.5 (Non-reasoning) | 11.11 | 43.09 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 206 | Anthropic | Claude 4.5 Sonnet (Non-reasoning) | 11.11 | 37.14 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 207 | Anthropic | Claude 4.5 Sonnet (Reasoning) | 11.11 | 43.03 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 208 | Anthropic | Claude Opus 4.5 (Reasoning) | 11.11 | 49.73 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 209 | Mistral | Devstral Medium | 11.11 | 18.66 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 210 | Mistral | Mistral Medium 3.1 | 11.11 | 21.25 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 211 | xAI | Grok 4 Fast (Non-reasoning) | 11.11 | 23.12 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 212 | Amazon | Nova Pro | 11.11 | 13.48 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 213 | Amazon | Nova Lite | 11.11 | 12.65 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 214 | OpenAI | o3 | 5.56 | 38.37 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 215 | Google | Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) | 5.56 | 21.65 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 216 | Google | Gemini 2.5 Pro | 5.56 | 34.63 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 217 | xAI | Grok 4.1 Fast (Reasoning) | 5.56 | 38.61 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 218 | xAI | Grok Code Fast 1 | 5.56 | 28.74 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 219 | OpenAI | GPT-5 (minimal) | 5.56 | 23.89 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 220 | OpenAI | GPT-5 (medium) | 5.56 | 42.03 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 221 | OpenAI | GPT-5 Codex (high) | 5.56 | 44.63 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 222 | OpenAI | GPT-5.1 (high) | 5.56 | 47.70 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 223 | OpenAI | GPT-5 (high) | 5.56 | 44.63 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 224 | OpenAI | GPT-5 mini (high) | 5.56 | 41.17 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 225 | OpenAI | GPT-5 nano (high) | 5.56 | 26.83 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 226 | OpenAI | GPT-5 nano (minimal) | 5.56 | 13.84 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 227 | OpenAI | GPT-5 (low) | 5.56 | 39.20 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 228 | OpenAI | GPT-5 nano (medium) | 5.56 | 25.88 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 229 | OpenAI | GPT-5 mini (minimal) | 5.56 | 20.68 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 230 | OpenAI | GPT-5 mini (medium) | 5.56 | 38.94 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 231 | Google | Gemini 2.5 Flash Preview (Sep '25) (Reasoning) | 5.56 | 31.14 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 232 | Google | Gemini 3 Pro Preview (high) | 5.56 | 48.39 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 233 | xAI | Grok 4 Fast (Reasoning) | 5.56 | 35.06 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 234 | xAI | Grok 4 | 5.56 | 41.52 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
Explore Evaluations
Artificial Analysis Intelligence IndexA composite benchmark aggregating ten challenging evaluations to provide a holistic measure of AI capabilities across mathematics, science, coding, and reasoning.
GDPval-AA LeaderboardGDPval-AA is Artificial Analysis' evaluation framework for OpenAI's GDPval dataset. It tests AI models on real-world tasks across 44 occupations and 9 major industries. Models are given shell access and web browsing capabilities in an agentic loop via Stirrup to solve tasks, with Elo ratings derived from blind pairwise comparisons.
APEX-Agents-AA Benchmark LeaderboardArtificial Analysis' implementation of the APEX-Agents benchmark, testing AI agents on long-horizon, cross-application tasks in professional-services environments with realistic application tooling.
𝜏²-Bench Telecom Benchmark LeaderboardA dual-control conversational AI benchmark simulating technical support scenarios where both agent and user must coordinate actions to resolve telecom service issues.
Terminal-Bench Hard Benchmark LeaderboardAn agentic benchmark evaluating AI capabilities in terminal environments through software engineering, system administration, and data processing tasks.
SciCode Benchmark LeaderboardA scientist-curated coding benchmark featuring 288 test set subproblems from 80 laboratory problems across 16 scientific disciplines.
Artificial Analysis Long Context Reasoning Benchmark LeaderboardA challenging benchmark measuring language models' ability to extract, reason about, and synthesize information from long-form documents ranging from 10k to 100k tokens (measured using the cl100k_base tokenizer).
AA-Omniscience: Knowledge and Hallucination BenchmarkA benchmark measuring factual recall and hallucination across various economically relevant domains.
IFBench Benchmark LeaderboardA benchmark evaluating precise instruction-following generalization on 58 diverse, verifiable out-of-domain constraints that test models' ability to follow specific output requirements.
Humanity's Last Exam Benchmark LeaderboardA frontier-level benchmark with 2,500 expert-vetted questions across mathematics, sciences, and humanities, designed to be the final closed-ended academic evaluation.
GPQA Diamond Benchmark Leaderboard
The most challenging 198 questions from GPQA, where PhD experts achieve 65% accuracy but skilled non-experts only reach 34% despite web access.
CritPt Benchmark LeaderboardA benchmark designed to test LLMs on research-level physics reasoning tasks, featuring 71 composite research challenges.
Artificial Analysis Openness IndexA composite measure providing an industry standard to communicate model openness for users and developers.
MMLU-Pro Benchmark LeaderboardAn enhanced version of MMLU with 12,000 graduate-level questions across 14 subject areas, featuring ten answer options and deeper reasoning requirements.
Global-MMLU-Lite Benchmark LeaderboardA lightweight, multilingual version of MMLU, designed to evaluate knowledge and reasoning skills across a diverse range of languages and cultural contexts.
LiveCodeBench Benchmark LeaderboardA contamination-free coding benchmark that continuously harvests fresh competitive programming problems from LeetCode, AtCoder, and CodeForces, evaluating code generation, self-repair, and execution.
MATH-500 Benchmark LeaderboardA 500-problem subset from the MATH dataset, featuring competition-level mathematics across six domains including algebra, geometry, and number theory.
AIME 2025 Benchmark LeaderboardAll 30 problems from the 2025 American Invitational Mathematics Examination, testing olympiad-level mathematical reasoning with integer answers from 000-999.
MMMU-Pro Benchmark LeaderboardAn enhanced MMMU benchmark that eliminates shortcuts and guessing strategies to more rigorously test multimodal models across 30 academic disciplines.