GDPval-AA leaderboard
- models measured
- 117
- lead over #2
- +6 Elo
- median
- 1133
Leader on GDPval-AA · read November 14
On November 14, 2026, 124 of our catalog's models had a GDPval-AA result, and Anthropic Claude Opus 5.5 led with 1866, ahead of MoonshotAI Kimi K3.1 Pro at 1861.
Real work tasks from professional occupations, with answers compared head to head. The number is an Elo rating. Run by Artificial Analysis on its own harness.
Role in the index
GDPval-AA is shown as published and does not feed any of our indexes. Read the methodology
| # | Model | Result | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5Anthropic | 1866 | 87.3 | $20.00 | |
| 2 | Kimi K3.1 ProMoonshot AI | 1861 | 79.0 | $10.00 | |
| 3 | Claude Sonnet 5.5Anthropic | 1838 | 84.3 | $10.00 | |
| 4 | Claude Fable 5.2Anthropic | 1831 | 87.8 | $40.00 | |
| 5 | Muse WonderMeta | 1770 | 71.8 | $20.00 | |
| 6 | Claude Fable 5.1Anthropic | 1765 | 82.8 | $50.00 | |
| 7 | DeepSeek V4.1 Flash 1017DeepSeek | 1746 | 66.9 | $0.60 | |
| 8 | Gemini 4 CarbonGoogle | 1733 | 86.6 | $10.00 | |
| 9 | Claude Opus 5Anthropic | 1729 | 81.7 | $25.00 | |
| 10 | Grok 4.7xAI | 1718 | 64.8 | $6.00 | |
| 11 | MiMo-V2.6-ProXiaomi | 1692 | 61.8 | $0.87 | |
| 12 | Muse Spark 1.3Meta | 1681 | 56.1 | $4.25 | |
| 13 | Qwen3.8 Max (0902)Qwen | 1674 | 67.3 | $6.00 | |
| 14 | Grok 4.6xAI | 1658 | 63.9 | $6.00 | |
| 15 | Ling 3.1 FlashinclusionAI | 1655 | Not benchmarked | $0.135 | |
| 16 | GLM 5.3Z.ai | 1655 | 68.5 | $4.40 | |
| 17 | GLM 5.3 FlashZ.ai | 1648 | 56.2 | $0.50 | |
| 18 | Gemini 4 ArgonGoogle | 1634 | 80.3 | $10.00 | |
| 19 | T Inkling 2 SmallThinking Machines | 1630 | 48.9 | $1.00 | |
| 20 | Claude Haiku 5.5Anthropic | 1629 | 68.4 | $0.50 | |
| 21 | GPT-5.6 SolOpenAI | 1619 | 70.6 | $20.00 | |
| 22 | Claude Fable 5Anthropic | 1618 | 75.9 | $50.00 | |
| 23 | MiMo-V2.6-FlashXiaomi | 1615 | 54.8 | $0.28 | |
| 24 | Qwen3.8 2.4T A95BQwen | 1614 | Not benchmarked | $6.00 | |
| 25 | GPT-6.1 SolOpenAI | 1607 | 79.8 | $10.00 | |
| 26 | DeepSeek V4.1 FlashDeepSeek | 1600 | 56.6 | $0.79 | |
| 27 | Step 5 PreviewStepFun | 1591 | 57.4 | $2.70 | |
| 28 | GPT-6 AstraOpenAI | 1587 | 83.8 | $50.00 | |
| 29 | DeepSeek V4 Flash Vision ExpDeepSeek | 1555 | Not benchmarked | $0.9834 | |
| 30 | Kimi K3Moonshot AI | 1542 | 61.4 | $15.00 | |
| 31 | GPT-6 SolOpenAI | 1514 | 72.1 | $10.00 | |
| 32 | Muse Spark 1.2Meta | 1478 | 50.9 | $4.25 | |
| 33 | GPT-6.1 TerraOpenAI | 1476 | 76.4 | $5.00 | |
| 34 | Claude Sonnet 5Anthropic | 1470 | 54.6 | $10.00 | |
| 35 | GPT-5.6 LunaOpenAI | 1470 | 55.3 | $1.20 | |
| 36 | MiniMax M3.1 FlashMiniMax | 1465 | 55.7 | $0.60 | |
| 37 | Claude Opus 4.8Anthropic | 1461 | 62.8 | $25.00 | |
| 38 | GPT-5.6 TerraOpenAI | 1461 | 63.5 | $12.00 | |
| 39 | DeepSeek V4 Pro 0813DeepSeek | 1456 | 56.1 | $1.98 | |
| 40 | GPT-6 LunaOpenAI | 1443 | 54.9 | $0.50 | |
| 41 | Gemini 3.8 FlashGoogle | 1442 | 60.3 | $3.75 | |
| 42 | DeepSeek V4 Flash 0731DeepSeek | 1437 | 51.8 | $0.348 | |
| 43 | Qwen3.8 27BQwen | 1426 | 69.7 | $2.55 | |
| 44 | Gemini 3.7 FlashGoogle | 1404 | 53.9 | $3.75 | |
| 45 | Muse Spark OpenMeta | 1401 | 43.4 | $4.25 | |
| 46 | Grok 4.5xAI | 1388 | 52.3 | $6.00 | |
| 47 | GLM 5.2Z.ai | 1380 | 61.1 | $4.40 | |
| 48 | Claude Opus 4.7Anthropic | 1361 | 67.5 | $25.00 | |
| 49 | GPT-5.5OpenAI | 1357 | 67.9 | $30.00 | |
| 50 | Gemini 3.6 FlashGoogle | 1293 | 62.5 | $3.75 | |
| 51 | GPT-5.4OpenAI | 1256 | 64.3 | $15.00 | |
| 52 | MiniMax M3MiniMax | 1250 | 33.6 | $1.20 | |
| 53 | Claude Sonnet 4.6Anthropic | 1240 | 55.0 | $15.00 | |
| 54 | Muse Spark 1.1Meta | 1216 | 70.2 | $4.25 | |
| 55 | Gemini 3.5 FlashGoogle | 1211 | 39.8 | $9.00 | |
| 56 | Ling 3.0 Flash VLinclusionAI | 1167 | Not benchmarked | $0.18 | |
| 57 | Nemotron 3.5 Super VLNVIDIA | 1162 | 14.8 | $0.50 | |
| 58 | Qwen3.7 MaxQwen | 1134 | 54.1 | $4.425 | |
| 59 | T Inkling SmallThinking Machines | 1133 | 27.3 | $1.20 | |
| 60 | MiMo-V2.5-ProXiaomi | 1128 | 31.5 | $1.335 | |
| 61 | M Motif 3Motif Technologies | 1127 | Not benchmarked | $1.20 | |
| 62 | GLM 5.1Z.ai | 1125 | 49.2 | $4.40 | |
| 63 | Ling 3.0 Flash FinRetiredinclusionAI | 1107 | Not benchmarked | $0.1232 | |
| 64 | Solar Pro 4Upstage | 1106 | Not benchmarked | $0.60 | |
| 65 | Solar Mini 4Upstage | 1092 | Not benchmarked | $0.20 | |
| 66 | T InklingThinking Machines | 1080 | 29.2 | $4.05 | |
| 67 | Hy3Tencent | 1069 | Not benchmarked | $0.528 | |
| 68 | Kimi K2.6Moonshot AI | 1046 | 52.1 | $4.00 | |
| 69 | Kimi K2.7 CodeMoonshot AI | 1046 | 53.4 | $4.00 | |
| 70 | GLM 4.7Z.ai | 1021 | 55.0 | $2.20 | |
| 71 | GPT-5.4 MiniOpenAI | 1021 | 35.8 | $4.50 | |
| 72 | Nemotron 3 UltraNVIDIA | 1020 | 30.0 | $2.30 | |
| 73 | MiniMax M2.7MiniMax | 1015 | 36.2 | $1.32 | |
| 74 | MiMo-V2.5Xiaomi | 1004 | 50.0 | $2.00 | |
| 75 | Qwen3.6 PlusQwen | 997 | 44.1 | $1.95 | |
| 76 | Gemini 3.5 Flash LiteGoogle | 994 | 48.9 | $2.50 | |
| 77 | Qwen3.6 27BQwen | 993 | 36.8 | $2.70 | |
| 78 | Ling 3.0 FlashinclusionAI | 956 | 29.6 | $0.1215 | |
| 79 | GPT-5.4 NanoOpenAI | 954 | 44.8 | $1.25 | |
| 80 | Grok 4.3xAI | 949 | 37.4 | $2.50 | |
| 81 | GPT-5OpenAI | 925 | 38.8 | $10.00 | |
| 82 | Qwen3.6 35B A3BQwen | 899 | Not benchmarked | $0.925 | |
| 83 | LongCat 2.0Meituan | 876 | Not benchmarked | $1.20 | |
| 84 | Step 3.7 FlashStepFun | 864 | Not benchmarked | $1.15 | |
| 85 | Kimi K2.5Moonshot AI | 847 | 38.6 | $2.85 | |
| 86 | GPT-5.1OpenAI | 834 | 40.5 | $10.00 | |
| 87 | Qwen3.5-122B-A10BQwen | 821 | Not benchmarked | $2.08 | |
| 88 | Qwen3.5 397B A17BQwen | 800 | Not benchmarked | $2.34 | |
| 89 | Gemini 3.1 Pro PreviewGoogle | 799 | 32.3 | $12.00 | |
| 90 | Qwen3.7 PlusQwen | 774 | 33.2 | $1.28 | |
| 91 | GPT-5 MiniOpenAI | 773 | 34.2 | $2.00 | |
| 92 | Mistral Medium 3.5Mistral AI | 769 | 25.4 | $7.50 | |
| 93 | GLM 4.6Z.ai | 764 | 8.9 | $2.20 | |
| 94 | DeepSeek V3.1 TerminusDeepSeek | 718 | Not benchmarked | $1.00 | |
| 95 | DeepSeek V3.2DeepSeek | 699 | 30.0 | $0.40 | |
| 96 | Nemotron 3.5 LightningNVIDIA | 645 | 22.6 | $0.18 | |
| 97 | Gemma 4 31BGoogle | 627 | 21.9 | $0.40 | |
| 98 | Qwen3.5-35B-A3BQwen | 616 | Not benchmarked | $1.30 | |
| 99 | gpt-oss-120bOpenAI | 615 | Not benchmarked | $0.45 | |
| 100 | Gemma 4 26B A4BGoogle | 573 | Not benchmarked | $0.60 | |
| 101 | Ling 3.0 TinyinclusionAI | 568 | Not benchmarked | $0.045 | |
| 102 | Command ACohere | 522 | Not benchmarked | $10.00 | |
| 103 | Qwen3 Coder NextQwen | 521 | Not benchmarked | $0.80 | |
| 104 | Mercury 2RetiredInception | 501 | Not benchmarked | $0.75 | |
| 105 | Granite 4.2 8BIBM Granite | 498 | Not benchmarked | $0.20 | |
| 106 | Nemotron 3 SuperNVIDIA | 497 | Not benchmarked | $0.425 | |
| 107 | Mercury 2.5RetiredInception | 482 | 1.6 | $0.15 | |
| 108 | Gemini 2.5 ProGoogle | 463 | 19.2 | $10.00 | |
| 109 | Gemini 3.1 Flash LiteGoogle | 438 | Not benchmarked | $1.50 | |
| 110 | Qwen3.5-9BQwen | 426 | Not benchmarked | $0.15 | |
| 111 | Mistral Medium 3.1Mistral AI | 392 | Not benchmarked | $2.00 | |
| 112 | Mistral Small 4Mistral AI | 369 | Not benchmarked | $0.60 | |
| 113 | gpt-oss-20bOpenAI | 347 | Not benchmarked | $0.14 | |
| 114 | Trinity Large ThinkingRetiredArcee AI | 343 | Not benchmarked | $0.80 | |
| 115 | Qwen3 235B A22B Instruct 2507Qwen | 320 | Not benchmarked | $0.675 | |
| 116 | GPT-4.1 MiniOpenAI | 277 | Not benchmarked | $1.60 | |
| 117 | Solar Pro 3RetiredUpstage | 272 | Not benchmarked | $0.60 | |
| 118 | Nemotron 3 Nano 30B A3BNVIDIA | 262 | Not benchmarked | $0.24 | |
| 119 | o3 MiniRetiredOpenAI | 237 | Not benchmarked | $4.40 | |
| 120 | Claude 3.5 HaikuRetiredAnthropic | 218 | Not benchmarked | $4.00 | |
| 121 | Qwen3 Next 80B A3B InstructQwen | 136 | Not benchmarked | $1.10 | |
| 122 | DeepSeek V3 0324DeepSeek | 76 | Not benchmarked | $1.07 | |
| 123 | Qwen3 30B A3B Instruct 2507Qwen | 75 | Not benchmarked | $0.30 | |
| 124 | Qwen3 32BQwen | 41 | Not benchmarked | $0.40 |
Only models in our catalog are listed, and each appears once with its best published run. 214 rows were read from the source on November 14, 2026, and rows that match no catalog model are left out.