AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
Artificial Analysis
Agentic real-world work tasks
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| Claude Opus 5 (Adaptive Reasoning, Max Effort) | 1834.67 | Not recorded | Not recorded | 2026-07-24 · model_announcement | Artificial Analysis |
| Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) | 1811.01 | Not recorded | Not recorded | 2026-07-24 · model_announcement | Artificial Analysis |
| GLM-5.3 (max) | 1765.86 | Not recorded | Not recorded | 2026-08-18 · model_announcement | Artificial Analysis |
| Grok 4.6 (xhigh) | 1761.27 | Not recorded | Not recorded | 2026-08-12 · model_announcement | Artificial Analysis |
| Grok 4.6 (high) | 1741.76 | Not recorded | Not recorded | 2026-08-12 · model_announcement | Artificial Analysis |
| Grok 4.6 (medium) | 1739.55 | Not recorded | Not recorded | 2026-08-12 · model_announcement | Artificial Analysis |
| Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | 1730.83 | Not recorded | Not recorded | 2026-06-09 · model_announcement | Artificial Analysis |
| Qwen3.8 Max | 1730.02 | Not recorded | Not recorded | 2026-08-03 · model_announcement | Artificial Analysis |
| Claude Opus 5 (Adaptive Reasoning, High Effort) | 1725.71 | Not recorded | Not recorded | 2026-07-24 · model_announcement | Artificial Analysis |
| Qwen3.8 2.4T A95B | 1716.91 | Not recorded | Not recorded | 2026-08-12 · model_announcement | Artificial Analysis |
| GPT-5.6 Sol (max) | 1716 | Not recorded | Not recorded | 2026-07-09 · model_announcement | Artificial Analysis |
| Kimi K3 (max) | 1675.22 | Not recorded | Not recorded | 2026-07-16 · model_announcement | Artificial Analysis |
| GPT-5.6 Sol (xhigh) | 1675.09 | Not recorded | Not recorded | 2026-07-09 · model_announcement | Artificial Analysis |
| DeepSeek V4 Flash Vision (Reasoning, Max Effort) | 1674.88 | Not recorded | Not recorded | 2026-08-21 · model_announcement | Artificial Analysis |
| Muse Spark 1.2 (xhigh) | 1622.63 | Not recorded | Not recorded | 2026-08-05 · model_announcement | Artificial Analysis |
| GPT-5.6 Sol (high) | 1617.11 | Not recorded | Not recorded | 2026-07-09 · model_announcement | Artificial Analysis |
| Claude Opus 5 (Adaptive Reasoning, Medium Effort) | 1615.81 | Not recorded | Not recorded | 2026-07-24 · model_announcement | Artificial Analysis |
| Claude Sonnet 5 (Adaptive Reasoning, Max Effort) | 1592.63 | Not recorded | Not recorded | 2026-06-30 · model_announcement | Artificial Analysis |
| DeepSeek V4 Pro 0813 (Reasoning, Max Effort) | 1585.75 | Not recorded | Not recorded | 2026-08-13 · model_announcement | Artificial Analysis |
| Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | 1581.94 | Not recorded | Not recorded | 2026-05-28 · model_announcement | Artificial Analysis |
| GPT-5.6 Luna (max) | 1577.39 | Not recorded | Not recorded | 2026-07-09 · model_announcement | Artificial Analysis |
| GPT-5.6 Terra (max) | 1573.13 | Not recorded | Not recorded | 2026-07-09 · model_announcement | Artificial Analysis |
| GPT-5.6 Terra (xhigh) | 1572.09 | Not recorded | Not recorded | 2026-07-09 · model_announcement | Artificial Analysis |
| DeepSeek V4 Flash 0731 (Reasoning, Max Effort) | 1558.52 | Not recorded | Not recorded | 2026-07-31 · model_announcement | Artificial Analysis |
| Grok 4.6 (low) | 1552.39 | Not recorded | Not recorded | 2026-08-12 · model_announcement | Artificial Analysis |
| GPT-5.6 Sol (medium) | 1547.46 | Not recorded | Not recorded | 2026-07-09 · model_announcement | Artificial Analysis |
| Qwen3.8 27B (xhigh) | 1541.23 | Not recorded | Not recorded | 2026-08-14 · model_announcement | Artificial Analysis |
| Gemini 3.7 Flash (high) | 1527.11 | Not recorded | Not recorded | 2026-08-13 · model_announcement | Artificial Analysis |
| GPT-5.6 Luna (xhigh) | 1524.32 | Not recorded | Not recorded | 2026-07-09 · model_announcement | Artificial Analysis |
| Qwen3.8 27B (medium) | 1518.9 | Not recorded | Not recorded | 2026-08-14 · model_announcement | Artificial Analysis |
| Grok 4.5 (high) | 1518.37 | Not recorded | Not recorded | 2026-07-08 · model_announcement | Artificial Analysis |
| GPT-5.6 Terra (high) | 1509.49 | Not recorded | Not recorded | 2026-07-09 · model_announcement | Artificial Analysis |
| GLM-5.2 (max) | 1505.12 | Not recorded | Not recorded | 2026-06-16 · model_announcement | Artificial Analysis |
| Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort) | 1497.07 | Not recorded | Not recorded | 2026-06-30 · model_announcement | Artificial Analysis |
| Gemini 3.7 Flash (medium) | 1496.26 | Not recorded | Not recorded | 2026-08-13 · model_announcement | Artificial Analysis |
| Qwen3.8 27B (low) | 1489.11 | Not recorded | Not recorded | 2026-08-14 · model_announcement | Artificial Analysis |
| GPT-5.5 (xhigh) | 1488.58 | Not recorded | Not recorded | 2026-04-23 · model_announcement | Artificial Analysis |
| Claude Opus 4.7 (Adaptive Reasoning, Max Effort) | 1485.91 | Not recorded | Not recorded | 2026-04-16 · model_announcement | Artificial Analysis |
| GPT-5.6 Luna (high) | 1465 | Not recorded | Not recorded | 2026-07-09 · model_announcement | Artificial Analysis |
| GPT-5.5 (high) | 1464.04 | Not recorded | Not recorded | 2026-04-23 · model_announcement | Artificial Analysis |
| Claude Opus 5 (Adaptive Reasoning, Low Effort) | 1455.08 | Not recorded | Not recorded | 2026-07-24 · model_announcement | Artificial Analysis |
| Gemini 3.7 Flash (low) | 1452.41 | Not recorded | Not recorded | 2026-08-13 · model_announcement | Artificial Analysis |
| GPT-5.6 Sol (low) | 1442.67 | Not recorded | Not recorded | 2026-07-09 · model_announcement | Artificial Analysis |
| Gemini 3.6 Flash (high) | 1419.09 | Not recorded | Not recorded | 2026-07-21 · model_announcement | Artificial Analysis |
| GPT-5.6 Terra (medium) | 1406.21 | Not recorded | Not recorded | 2026-07-09 · model_announcement | Artificial Analysis |
| Claude Sonnet 5 (Adaptive Reasoning, High Effort) | 1400.85 | Not recorded | Not recorded | 2026-06-30 · model_announcement | Artificial Analysis |
| GLM-5.2 (Non-reasoning) | 1393.47 | Not recorded | Not recorded | 2026-06-16 · model_announcement | Artificial Analysis |
| GPT-5.4 (xhigh) | 1391.79 | Not recorded | Not recorded | 2026-03-05 · model_announcement | Artificial Analysis |
| MiniMax-M3 | 1384.32 | Not recorded | Not recorded | 2026-06-01 · model_announcement | Artificial Analysis |
| GPT-5.6 Sol (Non-reasoning) | 1380.37 | Not recorded | Not recorded | 2026-07-09 · model_announcement | Artificial Analysis |
| Muse Spark 1.1 (xhigh) | 1374.97 | Not recorded | Not recorded | 2026-07-09 · model_announcement | Artificial Analysis |
| Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) | 1373.82 | Not recorded | Not recorded | 2026-02-17 · model_announcement | Artificial Analysis |
| GPT-5.5 (medium) | 1373.59 | Not recorded | Not recorded | 2026-04-23 · model_announcement | Artificial Analysis |
| Claude Sonnet 5 (Non-reasoning, High Effort) | 1367.85 | Not recorded | Not recorded | 2026-06-30 · model_announcement | Artificial Analysis |
| Gemini 3.5 Flash (high) | 1341.34 | Not recorded | Not recorded | 2026-05-19 · model_announcement | Artificial Analysis |
| DeepSeek V4 Pro (Reasoning, Max Effort) | 1302.91 | Not recorded | Not recorded | 2026-04-24 · model_announcement | Artificial Analysis |
| Claude Sonnet 5 (Adaptive Reasoning, Medium Effort) | 1300.97 | Not recorded | Not recorded | 2026-06-30 · model_announcement | Artificial Analysis |
| DeepSeek V4 Pro (Reasoning, High Effort) | 1291.45 | Not recorded | Not recorded | 2026-04-24 · model_announcement | Artificial Analysis |
| Solar Pro 4 | 1273.32 | Not recorded | Not recorded | 2026-08-06 · model_announcement | Artificial Analysis |
| GPT-5.6 Luna (medium) | 1272.79 | Not recorded | Not recorded | 2026-07-09 · model_announcement | Artificial Analysis |
| Kimi K3 (low) | 1272.51 | Not recorded | Not recorded | 2026-07-16 · model_announcement | Artificial Analysis |
| Motif 3 | 1272.22 | Not recorded | Not recorded | 2026-08-12 · model_announcement | Artificial Analysis |
| Inkling Small | 1268.66 | Not recorded | Not recorded | 2026-07-30 · model_announcement | Artificial Analysis |
| Qwen3.7 Max | 1268.16 | Not recorded | Not recorded | 2026-05-19 · model_announcement | Artificial Analysis |
| G9v3-39A5B | 1265.22 | Not recorded | Not recorded | 2026-08-20 · model_announcement | Artificial Analysis |
| JT-4.1 Flash 236B A21B | 1264.88 | Not recorded | Not recorded | 2026-07-09 · model_announcement | Artificial Analysis |
| MiMo-V2.5-Pro | 1264.09 | Not recorded | Not recorded | 2026-04-22 · model_announcement | Artificial Analysis |
| GLM-5.1 (Reasoning) | 1257 | Not recorded | Not recorded | 2026-04-07 · model_announcement | Artificial Analysis |
| GPT-5.6 Terra (low) | 1256.34 | Not recorded | Not recorded | 2026-07-09 · model_announcement | Artificial Analysis |
| Motif 3 (Beta) | 1254.55 | Not recorded | Not recorded | 2026-07-14 · model_announcement | Artificial Analysis |
| Nex-N2-Pro | 1250.2 | Not recorded | Not recorded | 2026-06-02 · model_announcement | Artificial Analysis |
| GPT-5.6 Terra (Non-reasoning) | 1244.21 | Not recorded | Not recorded | 2026-07-09 · model_announcement | Artificial Analysis |
| Inkling (xhigh) | 1236.39 | Not recorded | Not recorded | 2026-07-15 · model_announcement | Artificial Analysis |
| Claude Sonnet 5 (Adaptive Reasoning, Low Effort) | 1219.17 | Not recorded | Not recorded | 2026-06-30 · model_announcement | Artificial Analysis |
| Grok Build 0.1 0616 | 1213.7 | Not recorded | Not recorded | 2026-06-16 · model_announcement | Artificial Analysis |
| Hy3 | 1213.42 | Not recorded | Not recorded | 2026-07-06 · model_announcement | Artificial Analysis |
| Qwen3.8 27B (Non-reasoning) | 1210.94 | Not recorded | Not recorded | 2026-08-14 · model_announcement | Artificial Analysis |
| Kimi K2.6 | 1191.42 | Not recorded | Not recorded | 2026-04-20 · model_announcement | Artificial Analysis |
| DeepSeek V4 Flash (Reasoning, Max Effort) | 1189.97 | Not recorded | Not recorded | 2026-04-24 · model_announcement | Artificial Analysis |
| Kimi K2.7 Code | 1188.52 | Not recorded | Not recorded | 2026-06-12 · model_announcement | Artificial Analysis |
| GPT-5.5 (low) | 1186.39 | Not recorded | Not recorded | 2026-04-23 · model_announcement | Artificial Analysis |
| Agnes 2.5 Pro Alpha | 1171.16 | Not recorded | Not recorded | 2026-07-24 · model_announcement | Artificial Analysis |
| GPT-5.4 mini (xhigh) | 1169.72 | Not recorded | Not recorded | 2026-03-17 · model_announcement | Artificial Analysis |
| GLM-4.7 (Reasoning) | 1167.84 | Not recorded | Not recorded | 2025-12-22 · model_announcement | Artificial Analysis |
| Nemotron 3 Ultra 550B A55B (Reasoning) | 1162.11 | Not recorded | Not recorded | 2026-06-04 · model_announcement | Artificial Analysis |
| MiniMax-M2.7 | 1159.2 | Not recorded | Not recorded | 2026-03-18 · model_announcement | Artificial Analysis |
| GPT-5.6 Luna (low) | 1155 | Not recorded | Not recorded | 2026-07-09 · model_announcement | Artificial Analysis |
| DeepSeek V4 Flash (Reasoning, High Effort) | 1154.53 | Not recorded | Not recorded | 2026-04-24 · model_announcement | Artificial Analysis |
| MiMo-V2.5 | 1150.17 | Not recorded | Not recorded | 2026-04-22 · model_announcement | Artificial Analysis |
| Muse Spark | 1146.99 | Not recorded | Not recorded | 2026-04-08 · model_announcement | Artificial Analysis |
| Gemini 3.5 Flash-Lite | 1140.01 | Not recorded | Not recorded | 2026-07-21 · model_announcement | Artificial Analysis |
| Qwen3.6 27B (Reasoning) | 1139.86 | Not recorded | Not recorded | 2026-04-22 · model_announcement | Artificial Analysis |
| Qwen3.6 Plus | 1139.13 | Not recorded | Not recorded | 2026-04-02 · model_announcement | Artificial Analysis |
| GPT-5.5 (Non-reasoning) | 1124.79 | Not recorded | Not recorded | 2026-04-23 · model_announcement | Artificial Analysis |
| Solar Open2 250B | 1123.74 | Not recorded | Not recorded | 2026-08-12 · model_announcement | Artificial Analysis |
| A.X-K2 | 1113.44 | Not recorded | Not recorded | 2026-08-12 · model_announcement | Artificial Analysis |
| Qwen3.6 27B (Non-reasoning) | 1110.07 | Not recorded | Not recorded | 2026-04-22 · model_announcement | Artificial Analysis |
| Ling 3.0 Flash | 1105.37 | Not recorded | Not recorded | 2026-08-04 · model_announcement | Artificial Analysis |
| GPT-5.4 nano (xhigh) | 1104.6 | Not recorded | Not recorded | 2026-03-17 · model_announcement | Artificial Analysis |
| Grok 4.3 (Non-reasoning) | 1098.41 | Not recorded | Not recorded | 2026-04-30 · model_announcement | Artificial Analysis |
| Grok 4.3 (high) | 1088.27 | Not recorded | Not recorded | 2026-04-30 · model_announcement | Artificial Analysis |
| GPT-5 (high) | 1084.99 | Not recorded | Not recorded | 2025-08-07 · model_announcement | Artificial Analysis |
| GPT-5.6 Luna (Non-reasoning) | 1074.06 | Not recorded | Not recorded | 2026-07-09 · model_announcement | Artificial Analysis |
| Qwen3.6 35B A3B (Reasoning) | 1056.42 | Not recorded | Not recorded | 2026-04-16 · model_announcement | Artificial Analysis |
| Claude 4.5 Sonnet (Reasoning) | 1055.81 | Not recorded | Not recorded | 2025-09-29 · model_announcement | Artificial Analysis |
| LongCat 2.0 | 1031.12 | Not recorded | Not recorded | 2026-06-29 · model_announcement | Artificial Analysis |
| Qwen3.6 35B A3B (Non-reasoning) | 1019.89 | Not recorded | Not recorded | 2026-04-16 · model_announcement | Artificial Analysis |
| Step 3.7 Flash | 1019.57 | Not recorded | Not recorded | 2026-05-29 · model_announcement | Artificial Analysis |
| Kimi K2.5 (Reasoning) | 1007.65 | Not recorded | Not recorded | 2026-01-27 · model_announcement | Artificial Analysis |
| GPT-5.1 (high) | 995.58 | Not recorded | Not recorded | 2025-11-13 · model_announcement | Artificial Analysis |
| Qwen3.5 122B A10B (Reasoning) | 986.89 | Not recorded | Not recorded | 2026-02-24 · model_announcement | Artificial Analysis |
| K-EXAONE 2.0 0803 | 979.09 | Not recorded | Not recorded | 2026-08-12 · model_announcement | Artificial Analysis |
| Qwen3.5 397B A17B (Reasoning) | 965.38 | Not recorded | Not recorded | 2026-02-16 · model_announcement | Artificial Analysis |
| Gemini 3.1 Pro Preview | 964.55 | Not recorded | Not recorded | 2026-02-19 · model_announcement | Artificial Analysis |
| Muse Glimmer (high) | 955.94 | Not recorded | Not recorded | 2026-08-10 · model_announcement | Artificial Analysis |
| Qwen3.7 Plus | 946.3 | Not recorded | Not recorded | 2026-06-01 · model_announcement | Artificial Analysis |
| GPT-5 mini (high) | 939.88 | Not recorded | Not recorded | 2025-08-07 · model_announcement | Artificial Analysis |
| GLM-4.6 (Reasoning) | 934.33 | Not recorded | Not recorded | 2025-09-30 · model_announcement | Artificial Analysis |
| Mistral Medium 3.5 | 933.27 | Not recorded | Not recorded | 2026-04-29 · model_announcement | Artificial Analysis |
| Ring-2.6-1T | 922.85 | Not recorded | Not recorded | 2026-05-08 · model_announcement | Artificial Analysis |
| Claude 4.5 Haiku (Reasoning) | 913.63 | Not recorded | Not recorded | 2025-10-15 · model_announcement | Artificial Analysis |
| KAT Coder Pro V2 | 906.98 | Not recorded | Not recorded | 2026-03-27 · model_announcement | Artificial Analysis |
| KAT-Coder-Pro V1 | 905.7 | Not recorded | Not recorded | 2025-11-11 · model_announcement | Artificial Analysis |
| Qwen3.5 122B A10B (Non-reasoning) | 893.94 | Not recorded | Not recorded | 2026-02-24 · model_announcement | Artificial Analysis |
| DeepSeek V3.1 Terminus (Reasoning) | 882.73 | Not recorded | Not recorded | 2025-09-22 · model_announcement | Artificial Analysis |
| Claude 4 Sonnet (Reasoning) | 874.08 | Not recorded | Not recorded | 2025-05-22 · model_announcement | Artificial Analysis |
| DeepSeek V3.2 (Reasoning) | 865.03 | Not recorded | Not recorded | 2025-12-01 · model_announcement | Artificial Analysis |
| G9v3-3B | 863.41 | Not recorded | Not recorded | 2026-07-23 · model_announcement | Artificial Analysis |
| MiMo-V2-Flash (Non-reasoning) | 841.8 | Not recorded | Not recorded | 2025-12-16 · model_announcement | Artificial Analysis |
| Nemotron 3.5 Lightning | 826.12 | Not recorded | Not recorded | 2026-08-11 · model_announcement | Artificial Analysis |
| Gemma 4 31B (Reasoning) | 810.86 | Not recorded | Not recorded | 2026-04-02 · model_announcement | Artificial Analysis |
| gpt-oss-120b (high) | 799.7 | Not recorded | Not recorded | 2025-08-05 · model_announcement | Artificial Analysis |
| Qwen3.5 35B A3B (Non-reasoning) | 799.16 | Not recorded | Not recorded | 2026-02-24 · model_announcement | Artificial Analysis |
| GPT-5.4 mini (Non-Reasoning) | 791 | Not recorded | Not recorded | 2026-03-17 · model_announcement | Artificial Analysis |
| Ling 3.0 Tiny | 774.27 | Not recorded | Not recorded | 2026-08-06 · model_announcement | Artificial Analysis |
| Gemma 4 26B A4B (Reasoning) | 767.38 | Not recorded | Not recorded | 2026-04-02 · model_announcement | Artificial Analysis |
| Gemma 4 31B (Non-reasoning) | 747.11 | Not recorded | Not recorded | 2026-04-02 · model_announcement | Artificial Analysis |
| Devstral 2 | 741.9 | Not recorded | Not recorded | 2025-12-09 · model_announcement | Artificial Analysis |
| GPT-5.4 nano (Non-Reasoning) | 736.92 | Not recorded | Not recorded | 2026-03-17 · model_announcement | Artificial Analysis |
| Devstral Small 2 | 733.79 | Not recorded | Not recorded | 2025-12-09 · model_announcement | Artificial Analysis |
| Qwen3 Coder Next | 717.56 | Not recorded | Not recorded | 2026-02-03 · model_announcement | Artificial Analysis |
| GPT-5.5 Instant (June 2026) | 716.09 | Not recorded | Not recorded | 2026-06-25 · model_announcement | Artificial Analysis |
| Command A+ | 713.76 | Not recorded | Not recorded | 2026-05-20 · model_announcement | Artificial Analysis |
| Mercury 2 | 698.64 | Not recorded | Not recorded | 2026-02-20 · model_announcement | Artificial Analysis |
| Nemotron 3 Super 120B A12B (Reasoning) | 698.64 | Not recorded | Not recorded | 2026-03-11 · model_announcement | Artificial Analysis |
| Nova 2.0 Pro Preview (medium) | 681.86 | Not recorded | Not recorded | 2025-11-27 · model_announcement | Artificial Analysis |
| EXAONE 4.5 33B | 681.51 | Not recorded | Not recorded | 2026-04-09 · model_announcement | Artificial Analysis |
| Gemini 2.5 Pro | 670.45 | Not recorded | Not recorded | 2025-06-05 · model_announcement | Artificial Analysis |
| HyperNova 60B 2605 | 657.78 | Not recorded | Not recorded | 2026-05-26 · model_announcement | Artificial Analysis |
| Nova 2.0 Pro Preview (low) | 653.95 | Not recorded | Not recorded | 2025-11-27 · model_announcement | Artificial Analysis |
| Gemini 3.1 Flash-Lite | 647.33 | Not recorded | Not recorded | 2026-03-03 · model_announcement | Artificial Analysis |
| Gemma 4 12B (Reasoning) | 643.79 | Not recorded | Not recorded | 2026-06-03 · model_announcement | Artificial Analysis |
| Qwen3.5 9B (Reasoning) | 643.74 | Not recorded | Not recorded | 2026-03-02 · model_announcement | Artificial Analysis |
| Mistral Large 3 | 640.54 | Not recorded | Not recorded | 2025-12-02 · model_announcement | Artificial Analysis |
| Mistral Medium 3.1 | 608.1 | Not recorded | Not recorded | 2025-08-12 · model_announcement | Artificial Analysis |
| Mistral Small 3.1 | 603.1 | Not recorded | Not recorded | 2025-03-17 · model_announcement | Artificial Analysis |
| K-EXAONE (Reasoning) | 589.58 | Not recorded | Not recorded | 2025-12-31 · model_announcement | Artificial Analysis |
| Nova 2.0 Lite (high) | 588.64 | Not recorded | Not recorded | 2025-10-29 · model_announcement | Artificial Analysis |
| Mistral Small 4 (Reasoning) | 588 | Not recorded | Not recorded | 2026-03-16 · model_announcement | Artificial Analysis |
| gpt-oss-20b (high) | 565.68 | Not recorded | Not recorded | 2025-08-05 · model_announcement | Artificial Analysis |
| Trinity Large Thinking | 562.51 | Not recorded | Not recorded | 2026-04-01 · model_announcement | Artificial Analysis |
| Nova 2.0 Pro Preview (Non-reasoning) | 561.79 | Not recorded | Not recorded | 2025-11-27 · model_announcement | Artificial Analysis |
| DiffusionGemma 26B A4B | 553.25 | Not recorded | Not recorded | 2026-06-10 · model_announcement | Artificial Analysis |
| Qwen3 235B A22B 2507 (Reasoning) | 546.83 | Not recorded | Not recorded | 2025-07-25 · model_announcement | Artificial Analysis |
| Ling 2.6 Flash | 544.89 | Not recorded | Not recorded | 2026-04-21 · model_announcement | Artificial Analysis |
| North Mini Code | 542.2 | Not recorded | Not recorded | 2026-06-09 · model_announcement | Artificial Analysis |
| Celeris-1 | 535.69 | Not recorded | Not recorded | 2026-07-24 · model_announcement | Artificial Analysis |
| DeepSeek R1 (Jan '25) | 529.99 | Not recorded | Not recorded | 2025-01-20 · model_announcement | Artificial Analysis |
| GPT-4.1 mini | 506.24 | Not recorded | Not recorded | 2025-04-14 · model_announcement | Artificial Analysis |
| Nemotron Cascade 2 30B A3B | 499.77 | Not recorded | Not recorded | 2026-03-19 · model_announcement | Artificial Analysis |
| Solar Pro 3 | 497.74 | Not recorded | Not recorded | 2026-04-06 · model_announcement | Artificial Analysis |
| NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) | 490.46 | Not recorded | Not recorded | 2025-12-15 · model_announcement | Artificial Analysis |
| Ministral 3 14B | 484.15 | Not recorded | Not recorded | 2025-12-02 · model_announcement | Artificial Analysis |
| o3-mini (high) | 470.92 | Not recorded | Not recorded | 2025-01-31 · model_announcement | Artificial Analysis |
| Nemotron 3 Nano Omni 30B A3B Reasoning | 466.42 | Not recorded | Not recorded | 2026-04-29 · model_announcement | Artificial Analysis |
| Claude 3.5 Haiku | 458.09 | Not recorded | Not recorded | 2024-10-22 · model_announcement | Artificial Analysis |
| Ministral 3 8B | 453.66 | Not recorded | Not recorded | 2025-12-02 · model_announcement | Artificial Analysis |
| Granite 4.1 30B | 429.74 | Not recorded | Not recorded | 2026-04-29 · model_announcement | Artificial Analysis |
| Magistral Medium 1.2 | 413.41 | Not recorded | Not recorded | 2025-09-18 · model_announcement | Artificial Analysis |
| gpt-oss-120b (low) | 411.95 | Not recorded | Not recorded | 2025-08-05 · model_announcement | Artificial Analysis |
| K2 Think V2 | 379.28 | Not recorded | Not recorded | 2025-12-15 · model_announcement | Artificial Analysis |
| Qwen3 Next 80B A3B (Reasoning) | 375.69 | Not recorded | Not recorded | 2025-09-11 · model_announcement | Artificial Analysis |
| DeepSeek V3 0324 | 324.57 | Not recorded | Not recorded | 2025-03-25 · model_announcement | Artificial Analysis |
| Qwen3 30B A3B 2507 (Reasoning) | 323.18 | Not recorded | Not recorded | 2025-07-30 · model_announcement | Artificial Analysis |
| Qwen3 32B (Reasoning) | 289.74 | Not recorded | Not recorded | 2025-04-28 · model_announcement | Artificial Analysis |
| Ministral 3 3B | 283.61 | Not recorded | Not recorded | 2025-12-02 · model_announcement | Artificial Analysis |
| Magistral Small 1.2 | 263.08 | Not recorded | Not recorded | 2025-09-17 · model_announcement | Artificial Analysis |
| LFM2.5-2.6B | 251.35 | Not recorded | Not recorded | 2026-08-04 · model_announcement | Artificial Analysis |
| GPT-4 | 239.21 | Not recorded | Not recorded | 2023-03-14 · model_announcement | Artificial Analysis |
| GPT-4o mini | 237.68 | Not recorded | Not recorded | 2024-07-18 · model_announcement | Artificial Analysis |
| Qwen3 14B (Reasoning) | 236.97 | Not recorded | Not recorded | 2025-04-28 · model_announcement | Artificial Analysis |
| DeepSeek V3 (Dec '24) | 231.74 | Not recorded | Not recorded | 2024-12-26 · model_announcement | Artificial Analysis |
| Gemma 4 E4B (Reasoning) | 228.91 | Not recorded | Not recorded | 2026-04-03 · model_announcement | Artificial Analysis |
| Qwen3.5 2B (Reasoning) | 215.63 | Not recorded | Not recorded | 2026-03-02 · model_announcement | Artificial Analysis |
| Qwen3 8B (Reasoning) | 214.87 | Not recorded | Not recorded | 2025-04-28 · model_announcement | Artificial Analysis |
| NVIDIA Nemotron 3 Nano 4B | 203.8 | Not recorded | Not recorded | 2026-03-16 · model_announcement | Artificial Analysis |
| Granite 4.1 3B | 122.77 | Not recorded | Not recorded | 2026-04-29 · model_announcement | Artificial Analysis |
| Llama 4 Scout | 108.34 | Not recorded | Not recorded | 2025-04-05 · model_announcement | Artificial Analysis |
| Llama 3.3 Instruct 70B | 96.3 | Not recorded | Not recorded | 2024-12-06 · model_announcement | Artificial Analysis |
| Gemma 4 E2B (Reasoning) | 85.98 | Not recorded | Not recorded | 2026-04-02 · model_announcement | Artificial Analysis |
| Mistral Small 3.2 | 78.83 | Not recorded | Not recorded | 2025-06-20 · model_announcement | Artificial Analysis |
| GPT-4.1 nano | 60.08 | Not recorded | Not recorded | 2025-04-14 · model_announcement | Artificial Analysis |
| Llama 4 Maverick | 3.81 | Not recorded | Not recorded | 2025-04-05 · model_announcement | Artificial Analysis |
| NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) | -72.59 | Not recorded | Not recorded | 2025-12-15 · model_announcement | Artificial Analysis |
| Qwen3.5 2B (Non-reasoning) | -81.03 | Not recorded | Not recorded | 2026-03-02 · model_announcement | Artificial Analysis |
| Qwen3.5 0.8B (Non-reasoning) | -82.62 | Not recorded | Not recorded | 2026-03-02 · model_announcement | Artificial Analysis |
| MiniCPM-V 4.6 1.3B | -85.86 | Not recorded | Not recorded | 2026-05-11 · model_announcement | Artificial Analysis |
| Llama 3.1 Instruct 8B | -102.28 | Not recorded | Not recorded | 2024-07-23 · model_announcement | Artificial Analysis |
| Qwen3.5 0.8B (Reasoning) | -103.02 | Not recorded | Not recorded | 2026-03-02 · model_announcement | Artificial Analysis |
| Nanbeige4.1-3B | -117 | Not recorded | Not recorded | 2026-02-11 · model_announcement | Artificial Analysis |
| Gemma 3 12B Instruct | -121.39 | Not recorded | Not recorded | 2025-03-12 · model_announcement | Artificial Analysis |
| Gemma 3 27B Instruct | -122.08 | Not recorded | Not recorded | 2025-03-12 · model_announcement | Artificial Analysis |
| Phi-4 Mini Instruct | -122.53 | Not recorded | Not recorded | 2024-02-26 · model_announcement | Artificial Analysis |