AI benchmark results and model performance
Individual benchmark scores plotted by date.
| Organisation | Model | Reported | Top Score | Info | Self Reported | Source |
|---|---|---|---|---|---|---|
| Mistral Medium 3.1 | 12 Aug 2025 | 0.30 | sigma 0.289; games 310; avg points 0.250 | No | Source | |
| Qwen 3 30B A3B | - | 1.86 | sigma 0.212; games 535; avg points 0.358 | No | Source | |
| Gemini 2.0 Flash | 05 Feb 2025 | 1.95 | sigma 0.177; games 757; avg points 0.376 | No | Source | |
| QwQ 32B | - | 2.05 | 16K; sigma 0.203; games 586; avg points 0.382 | No | Source | |
| Mistral Medium 3.0 | 07 May 2025 | 2.19 | sigma 0.216; games 510; avg points 0.374 | No | Source | |
| GLM 4.6 | 30 Sept 2025 | 2.69 | sigma 0.584; games 70; avg points 0.386 | No | Source | |
| Gemini 2.0 Flash Thinking Exp (2025-01-21) | 21 Jan 2025 | 2.81 | sigma 0.213; games 522; avg points 0.449 | No | Source | |
| Phi 4 | 12 Dec 2024 | 2.84 | sigma 0.136; games 1254; avg points 0.425 | No | Source | |
| Gemini 2.0 Pro Exp (2025-02-05) | 05 Feb 2025 | 3.07 | sigma 0.218; games 494; avg points 0.462 | No | Source | |
| Llama 3.1 405B Instruct | 23 Jul 2024 | 3.07 | sigma 0.172; games 784; avg points 0.459 | No | Source | |
| Claude 3.5 Haiku | 04 Nov 2024 | 3.15 | sigma 0.139; games 1193; avg points 0.452 | No | Source | |
| o4 Mini | 16 Apr 2025 | 3.30 | High reasoning; sigma 0.209; games 534; avg points 0.445 | No | Source | |
| GPT 4o Mini (2024-07-18) | 18 Jul 2024 | 3.30 | sigma 0.144; games 1114; avg points 0.462 | No | Source | |
| Grok 2 | 13 Aug 2024 | 3.35 | sigma 0.171; games 792; avg points 0.475 | No | Source | |
| Mistral Small 3.0 | 30 Jan 2025 | 3.39 | sigma 0.161; games 889; avg points 0.475 | No | Source | |
| Kimi K2 (2025-09-05) | 05 Sept 2025 | 3.40 | sigma 0.252; games 378; avg points 0.455 | No | Source | |
| Minimax Text 01 | 15 Jan 2025 | 3.45 | sigma 0.131; games 1335; avg points 0.471 | No | Source | |
| Qwen 3 235B A22B | - | 3.52 | sigma 0.205; games 558; avg points 0.464 | No | Source | |
| Nova Pro 1.0 | 04 Dec 2024 | 3.52 | sigma 0.135; games 1253; avg points 0.477 | No | Source | |
| Llama 3.3 70B Instruct | 06 Dec 2024 | 3.59 | sigma 0.166; games 836; avg points 0.493 | No | Source | |
| Grok 4.1 Thinking | 17 Nov 2025 | 3.62 | Fast reasoning; sigma 0.246; games 385; avg points 0.455 | No | Source | |
| Llama 4 Maverick | 05 Apr 2025 | 3.63 | sigma 0.142; games 1146; avg points 0.474 | No | Source | |
| Mistral Large 3.0 | 02 Dec 2025 | 3.64 | sigma 0.262; games 337; avg points 0.456 | No | Source | |
| GPT OSS 120b | 05 Aug 2025 | 3.79 | sigma 0.210; games 519; avg points 0.462 | No | Source | |
| o1 | 17 Dec 2024 | 3.86 | Medium reasoning; sigma 0.171; games 798; avg points 0.510 | No | Source |