Vals Index v2.2
The official leaderboard hasn’t scored a model released after Gemini 4 Neon (November 2026). Labs report their own numbers for one newer model: Inkling 2 Mini at 46.5%.
Agents are scored on eight finance, coding, legal, and tax benchmarks, combined with weights from each sector's share of US GDP.
Version 2.2 from 19 October 2026: (8.0 × finance + 5.6 × coding + 1.2 × legal + 0.5 × tax) / 15.3. Finance averages Finance Agent v2.1 and EMB v1.1. Coding averages Terminal-Bench 4, Vibe Code Bench v1.1 and Code Migration v1.1. Legal averages Legal Research and HLAB-Vals-1.1. Tax is Tax Agent Bench (all-pass accuracy). Six of the eight components are private. Earlier versions have their own records.
- Made by
- Vals AI
- Released
- October 2026
- Kind
- Composite work indices
- Scored
- Graded by a model
- Answers
- Agent task
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- Terminal, APIs and tools
- Items from
- Another benchmark
- Refresh
- New versions replace it
- Run by
- A host
- Based on
- Vals Index v2.1
- Combines
- Harvey LAB v1.1 (HLAB-Vals-1.1), Legal Research Bench, Terminal-Bench 4.0, Code Migration v1.1, Excel Modeling Benchmark v1.1, Vals Finance Agent v2.1, Tax Agent Bench
- In views
- Agents, Law and finance
- Strongest model tested
- GPT-6.2 Astra #1 on the capability index
- Last in a launch post
- November 2026
- Last model added
- November 2026
- Scores refreshed
- November 19th, 2026
Claude Fable 5.2 leads with 71.3% Claude Fable 5.2 leads with 71.3%
Best score per entry from the benchmark's own leaderboard, read on November 19th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
Claude Fable 5.2 leads with 71.3%, claims included
Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model. Striped bars are claims, and dotted bars are reruns by Epoch AI or another board.
- 71.3 Claude Fable 5.2
- 70.9
Gemini 4 Neon
- 70.8 Claude Sonnet 5.5
- 70.5
Gemini 4 Carbon
- 70.1 Claude Opus 5.5
- 69.4
Gemini 4 Argon
- 68.5
Gemini 4 Hydrogen
- 67.7 GPT-6.2 Astra
- 66.8
Muse Wonder Full
- 66.1 GPT-6.2 Sol
- 65.0 GPT-6 Astra
- 64.9
Muse Wonder
- 63.9 GPT-6.1 Sol
- 63.2
Qwen4-Max
- 62.5 Kimi K3.1 Pro
- 61.3
DeepSeek V4.1 Flash 1017
- 60.5 GPT-6.1 Terra
- 60.5
Muse Ember
- 59.9 GLM-5.3
- 59.4
Tencent Hy4
- 59.0
Qwen3.8 Max (0902)
- 58.7 Claude Haiku 5.5
- 58.6 Grok 4.7
- 57.8 MiMo-V2.6 Pro
- 56.5
Mistral Large 4
- 56.1
Inkling 2 Small
- 56.0
Gemini 3.8 Flash
- 54.8 MiMo-V2.6 Flash
- 54.8
Step 5 Preview
- 53.8
MiniMax-M3.1-Flash
- 53.2
Tencent Hy4 preview
- 53.0
DeepSeek V4 Pro 0813
- 53.0 Kimi K3
- 52.3 GPT-6 Luna
- 50.9 GLM-5.3-Flash
- 50.8 Hy4 Flash
- 48.6
Muse Spark Open
- 43.7 Mercury 3
- 43.4 Beam 1.0
- 29.8
Nemotron 3.5 Super VL
- 29.0
Inkling
- 27.6
Inkling-Small
- 1 Claude Fable 5.2 71.3%
- 2
Gemini 4 Neon 70.9%
- 3 Claude Sonnet 5.5 70.8%
- 4
Gemini 4 Carbon 70.5%
- 5 Claude Opus 5.5 70.1%
- 6
Gemini 4 Argon 69.4%
- 7
Gemini 4 Hydrogen 68.5%
- 8 GPT-6.2 Astra 67.7%
- 9
Muse Wonder Full 66.8%
- 10 GPT-6.2 Sol 66.1%
- 11 GPT-6 Astra 65%
- 12
Muse Wonder 64.9%
- 13 GPT-6.1 Sol 63.9%
- 14
Qwen4-Max 63.2%
- 15 Kimi K3.1 Pro 62.5%
- 16
DeepSeek V4.1 Flash 1017 61.3%
- 17 GPT-6.1 Terra 60.5%
- 18
Muse Ember 60.5%
- 19 GLM-5.3 59.9%
- 20
Tencent Hy4 59.4%
- 21
Qwen3.8 Max (0902) 59%
- 22 Claude Haiku 5.5 58.7%
- 23 Grok 4.7 58.6%
- 24 MiMo-V2.6 Pro 57.8%
- 25
Mistral Large 4 56.5%
- 26
Inkling 2 Small 56.1%
- 27
Gemini 3.8 Flash 56%
- 28 MiMo-V2.6 Flash 54.8%
- 29
Step 5 Preview 54.8%
- 30
MiniMax-M3.1-Flash 53.8%
- 31
Tencent Hy4 preview 53.2%
- 32
DeepSeek V4 Pro 0813 53%
- 33 Kimi K3 53%
- 34 GPT-6 Luna 52.3%
- 35 GLM-5.3-Flash 50.9%
- 36 Hy4 Flash 50.8%
- 37
Muse Spark Open 48.6%
- 38 Mercury 3 43.7%
- 39 Beam 1.0 43.4%
- 40
Nemotron 3.5 Super VL 29.8%
- 41
Inkling 29%
- 42
Inkling-Small 27.6%
Source: Official Vals Index v2.2 leaderboard
- 71.3 Claude Fable 5.2
- 70.9
Gemini 4 Neon
- 70.8 Claude Sonnet 5.5
- 70.5
Gemini 4 Carbon
- 70.1 Claude Opus 5.5
- 69.4
Gemini 4 Argon
- 68.5
Gemini 4 Hydrogen
- 67.7 GPT-6.2 Astra
- 66.8
Muse Wonder Full
- 66.1 GPT-6.2 Sol
- 65.0 GPT-6 Astra
- 64.9
Muse Wonder
- 63.9 GPT-6.1 Sol
- 63.2
Qwen4-Max
- 62.5 Kimi K3.1 Pro
- 61.3
DeepSeek V4.1 Flash 1017
- 60.5 GPT-6.1 Terra
- 60.5
Muse Ember
- 59.9 GLM-5.3
- 59.4
Tencent Hy4
- 59.0
Qwen3.8 Max (0902)
- 58.7 Claude Haiku 5.5
- 58.6 Grok 4.7
- 57.8 MiMo-V2.6 Pro
- 56.5
Mistral Large 4
- 56.1
Inkling 2 Small
- 56.0
Gemini 3.8 Flash
- 54.8 MiMo-V2.6 Flash
- 54.8
Step 5 Preview
- 53.8
MiniMax-M3.1-Flash
- 53.2
Tencent Hy4 preview
- 53.0
DeepSeek V4 Pro 0813
- 53.0 Kimi K3
- 52.3 GPT-6 Luna
- 50.9 GLM-5.3-Flash
- 48.6
Muse Spark Open
- 43.7 Mercury 3
- 43.4 Beam 1.0
- 29.8
Nemotron 3.5 Super VL
- 29.0
Inkling
- 27.6
Inkling-Small
- 1 Claude Fable 5.2 71.3%
- 2
Gemini 4 Neon 70.9%
- 3 Claude Sonnet 5.5 70.8%
- 4
Gemini 4 Carbon 70.5%
- 5 Claude Opus 5.5 70.1%
- 6
Gemini 4 Argon 69.4%
- 7
Gemini 4 Hydrogen 68.5%
- 8 GPT-6.2 Astra 67.7%
- 9
Muse Wonder Full 66.8%
- 10 GPT-6.2 Sol 66.1%
- 11 GPT-6 Astra 65%
- 12
Muse Wonder 64.9%
- 13 GPT-6.1 Sol 63.9%
- 14
Qwen4-Max 63.2%
- 15 Kimi K3.1 Pro 62.5%
- 16
DeepSeek V4.1 Flash 1017 61.3%
- 17 GPT-6.1 Terra 60.5%
- 18
Muse Ember 60.5%
- 19 GLM-5.3 59.9%
- 20
Tencent Hy4 59.4%
- 21
Qwen3.8 Max (0902) 59%
- 22 Claude Haiku 5.5 58.7%
- 23 Grok 4.7 58.6%
- 24 MiMo-V2.6 Pro 57.8%
- 25
Mistral Large 4 56.5%
- 26
Inkling 2 Small 56.1%
- 27
Gemini 3.8 Flash 56%
- 28 MiMo-V2.6 Flash 54.8%
- 29
Step 5 Preview 54.8%
- 30
MiniMax-M3.1-Flash 53.8%
- 31
Tencent Hy4 preview 53.2%
- 32
DeepSeek V4 Pro 0813 53%
- 33 Kimi K3 53%
- 34 GPT-6 Luna 52.3%
- 35 GLM-5.3-Flash 50.9%
- 36
Muse Spark Open 48.6%
- 37 Mercury 3 43.7%
- 38 Beam 1.0 43.4%
- 39
Nemotron 3.5 Super VL 29.8%
- 40
Inkling 29%
- 41
Inkling-Small 27.6%
Source: Official Vals Index v2.2 leaderboard
- 71.3 Claude Fable 5.2
- 70.9
Gemini 4 Neon
- 70.8 Claude Sonnet 5.5
- 70.5
Gemini 4 Carbon
- 70.1 Claude Opus 5.5
- 69.4
Gemini 4 Argon
- 68.5
Gemini 4 Hydrogen
- 67.7 GPT-6.2 Astra
- 66.8
Muse Wonder Full
- 66.1 GPT-6.2 Sol
- 65.0 GPT-6 Astra
- 64.9
Muse Wonder
- 63.9 GPT-6.1 Sol
- 63.2
Qwen4-Max
- 62.5 Kimi K3.1 Pro
- 61.3
DeepSeek V4.1 Flash 1017
- 60.5 GPT-6.1 Terra
- 60.5
Muse Ember
- 59.9 GLM-5.3
- 59.4
Tencent Hy4
- 59.0
Qwen3.8 Max (0902)
- 58.7 Claude Haiku 5.5
- 58.6 Grok 4.7
- 57.8 MiMo-V2.6 Pro
- 56.5
Mistral Large 4
- 56.1
Inkling 2 Small
- 56.0
Gemini 3.8 Flash
- 54.8 MiMo-V2.6 Flash
- 54.8
Step 5 Preview
- 53.8
MiniMax-M3.1-Flash
- 53.2
Tencent Hy4 preview
- 53.0
DeepSeek V4 Pro 0813
- 53.0 Kimi K3
- 52.3 GPT-6 Luna
- 50.9 GLM-5.3-Flash
- 48.6
Muse Spark Open
- 46.5
Inkling 2 Mini
- 43.7 Mercury 3
- 43.4 Beam 1.0
- 29.8
Nemotron 3.5 Super VL
- 29.0
Inkling
- 27.6
Inkling-Small
- 1 Claude Fable 5.2 71.3%
- 2
Gemini 4 Neon 70.9%
- 3 Claude Sonnet 5.5 70.8%
- 4
Gemini 4 Carbon 70.5%
- 5 Claude Opus 5.5 70.1%
- 6
Gemini 4 Argon 69.4%
- 7
Gemini 4 Hydrogen 68.5%
- 8 GPT-6.2 Astra 67.7%
- 9
Muse Wonder Full 66.8%
- 10 GPT-6.2 Sol 66.1%
- 11 GPT-6 Astra 65%
- 12
Muse Wonder 64.9%
- 13 GPT-6.1 Sol 63.9%
- 14
Qwen4-Max 63.2%
- 15 Kimi K3.1 Pro 62.5%
- 16
DeepSeek V4.1 Flash 1017 61.3%
- 17 GPT-6.1 Terra 60.5%
- 18
Muse Ember 60.5%
- 19 GLM-5.3 59.9%
- 20
Tencent Hy4 59.4%
- 21
Qwen3.8 Max (0902) 59%
- 22 Claude Haiku 5.5 58.7%
- 23 Grok 4.7 58.6%
- 24 MiMo-V2.6 Pro 57.8%
- 25
Mistral Large 4 56.5%
- 26
Inkling 2 Small 56.1%
- 27
Gemini 3.8 Flash 56%
- 28 MiMo-V2.6 Flash 54.8%
- 29
Step 5 Preview 54.8%
- 30
MiniMax-M3.1-Flash 53.8%
- 31
Tencent Hy4 preview 53.2%
- 32
DeepSeek V4 Pro 0813 53%
- 33 Kimi K3 53%
- 34 GPT-6 Luna 52.3%
- 35 GLM-5.3-Flash 50.9%
- 36
Muse Spark Open 48.6%
- 37
Inkling 2 Mini 46.5%
- 38 Mercury 3 43.7%
- 39 Beam 1.0 43.4%
- 40
Nemotron 3.5 Super VL 29.8%
- 41
Inkling 29%
- 42
Inkling-Small 27.6%
Sources: Official Vals Index v2.2 leaderboard and labs’ model cards
| # | Entry | Score ± 95% CI | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.2 | 71.3% ±1.9 | Nov 2026 | Official leaderboard | |
| 2 | | 70.9% ±1.8 | Nov 2026 | Official leaderboard | |
| 3 | Claude Sonnet 5.5 | 70.8% ±1.8 | Sep 2026 | Official leaderboard | |
| 4 | | 70.5% ±1.9 | Oct 2026 | Official leaderboard | |
| 5 | Claude Opus 5.5 | 70.1% ±2 | Sep 2026 | Official leaderboard | |
| 6 | | 69.4% ±2.1 | Sep 2026 | Official leaderboard | |
| 7 | | 68.5% ±1.9 | Nov 2026 | Official leaderboard | |
| 8 | GPT-6.2 Astra | 67.7% ±1.8 | Nov 2026 | Official leaderboard | |
| 9 | | 66.8% ±2.1 | Oct 2026 | Official leaderboard | |
| 10 | GPT-6.2 Sol | 66.1% ±1.8 | Nov 2026 | Official leaderboard | |
| 11 | GPT-6 Astra | 65% ±2.2 | Sep 2026 | Official leaderboard | |
| 12 | | 64.9% ±2.1 | Oct 2026 | Official leaderboard | |
| 13 | GPT-6.1 Sol | 63.9% ±2.1 | Sep 2026 | Official leaderboard | |
| 14 | | 63.2% ±2 | Nov 2026 | Official leaderboard | |
| 15 | Kimi K3.1 Pro | 62.5% ±2.2 | Oct 2026 | Official leaderboard | |
| 16 | | 61.3% ±2.1 | Oct 2026 | Official leaderboard | |
| 17 | GPT-6.1 Terra | 60.5% ±1.9 | Oct 2026 | Official leaderboard | |
| 18 | | 60.5% ±2.1 | Nov 2026 | Official leaderboard | |
| 19 | GLM-5.3 | 59.9% ±2.2 | Aug 2026 | Official leaderboard | |
| 20 | | 59.4% ±2.1 | Nov 2026 | Official leaderboard | |
| 21 | | 59% ±2.1 | Sep 2026 | Official leaderboard | |
| 22 | Claude Haiku 5.5 | 58.7% ±2.5 | Oct 2026 | Official leaderboard | |
| 23 | Grok 4.7 | 58.6% ±2 | Sep 2026 | Official leaderboard | |
| 24 | MiMo-V2.6 Pro | 57.8% ±2.4 | Sep 2026 | Official leaderboard | |
| 25 | | 56.5% ±2.5 | Oct 2026 | Official leaderboard | |
| 26 | | 56.1% ±2.3 | Nov 2026 | Official leaderboard | |
| 27 | | 56% ±2.2 | Sep 2026 | Official leaderboard | |
| 28 | MiMo-V2.6 Flash | 54.8% ±2.2 | Sep 2026 | Official leaderboard | |
| 29 | | 54.8% ±2.3 | Sep 2026 | Official leaderboard | |
| 30 | | 53.8% ±2.1 | Oct 2026 | Official leaderboard | |
| 31 | | 53.2% ±2.2 | Aug 2026 | Official leaderboard | |
| 32 | | 53% ±2 | Aug 2026 | Official leaderboard | |
| 33 | Kimi K3 | 53% ±2 | Jul 2026 | Official leaderboard | |
| 34 | GPT-6 Luna | 52.3% ±2.2 | Sep 2026 | Official leaderboard | |
| 35 | GLM-5.3-Flash | 50.9% ±2.5 | Aug 2026 | Official leaderboard | |
| 36 | Hy4 Flash | 50.8% ±2.1 | Official leaderboard | ||
| 37 | | 48.6% ±2.1 | Oct 2026 | Official leaderboard | |
| 38 | Mercury 3 | 43.7% ±2.4 | Oct 2026 | Official leaderboard | |
| 39 | Beam 1.0 | 43.4% ±2.1 | Oct 2026 | Official leaderboard | |
| 40 | | 29.8% ±2 | Oct 2026 | Official leaderboard | |
| 41 | | 29% ±2.2 | Jul 2026 | Official leaderboard | |
| 42 | | 27.6% ±2.2 | Jul 2026 | Official leaderboard |
| # | Model | Score ± 95% CI | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.2 | 71.3% ±1.9 | Nov 2026 | Official leaderboard | |
| 2 | | 70.9% ±1.8 | Nov 2026 | Official leaderboard | |
| 3 | Claude Sonnet 5.5 | 70.8% ±1.8 | Sep 2026 | Official leaderboard | |
| 4 | | 70.5% ±1.9 | Oct 2026 | Official leaderboard | |
| 5 | Claude Opus 5.5 | 70.1% ±2 | Sep 2026 | Official leaderboard | |
| 6 | | 69.4% ±2.1 | Sep 2026 | Official leaderboard | |
| 7 | | 68.5% ±1.9 | Nov 2026 | Official leaderboard | |
| 8 | GPT-6.2 Astra | 67.7% ±1.8 | Nov 2026 | Official leaderboard | |
| 9 | | 66.8% ±2.1 | Oct 2026 | Official leaderboard | |
| 10 | GPT-6.2 Sol | 66.1% ±1.8 | Nov 2026 | Official leaderboard | |
| 11 | GPT-6 Astra | 65% ±2.2 | Sep 2026 | Official leaderboard | |
| 12 | | 64.9% ±2.1 | Oct 2026 | Official leaderboard | |
| 13 | GPT-6.1 Sol | 63.9% ±2.1 | Sep 2026 | Official leaderboard | |
| 14 | | 63.2% ±2 | Nov 2026 | Official leaderboard | |
| 15 | Kimi K3.1 Pro | 62.5% ±2.2 | Oct 2026 | Official leaderboard | |
| 16 | | 61.3% ±2.1 | Oct 2026 | Official leaderboard | |
| 17 | GPT-6.1 Terra | 60.5% ±1.9 | Oct 2026 | Official leaderboard | |
| 18 | | 60.5% ±2.1 | Nov 2026 | Official leaderboard | |
| 19 | GLM-5.3 | 59.9% ±2.2 | Aug 2026 | Official leaderboard | |
| 20 | | 59.4% ±2.1 | Nov 2026 | Official leaderboard | |
| 21 | | 59% ±2.1 | Sep 2026 | Official leaderboard | |
| 22 | Claude Haiku 5.5 | 58.7% ±2.5 | Oct 2026 | Official leaderboard | |
| 23 | Grok 4.7 | 58.6% ±2 | Sep 2026 | Official leaderboard | |
| 24 | MiMo-V2.6 Pro | 57.8% ±2.4 | Sep 2026 | Official leaderboard | |
| 25 | | 56.5% ±2.5 | Oct 2026 | Official leaderboard | |
| 26 | | 56.1% ±2.3 | Nov 2026 | Official leaderboard | |
| 27 | | 56% ±2.2 | Sep 2026 | Official leaderboard | |
| 28 | MiMo-V2.6 Flash | 54.8% ±2.2 | Sep 2026 | Official leaderboard | |
| 29 | | 54.8% ±2.3 | Sep 2026 | Official leaderboard | |
| 30 | | 53.8% ±2.1 | Oct 2026 | Official leaderboard | |
| 31 | | 53.2% ±2.2 | Aug 2026 | Official leaderboard | |
| 32 | | 53% ±2 | Aug 2026 | Official leaderboard | |
| 33 | Kimi K3 | 53% ±2 | Jul 2026 | Official leaderboard | |
| 34 | GPT-6 Luna | 52.3% ±2.2 | Sep 2026 | Official leaderboard | |
| 35 | GLM-5.3-Flash | 50.9% ±2.5 | Aug 2026 | Official leaderboard | |
| 36 | | 48.6% ±2.1 | Oct 2026 | Official leaderboard | |
| 37 | Mercury 3 | 43.7% ±2.4 | Oct 2026 | Official leaderboard | |
| 38 | Beam 1.0 | 43.4% ±2.1 | Oct 2026 | Official leaderboard | |
| 39 | | 29.8% ±2 | Oct 2026 | Official leaderboard | |
| 40 | | 29% ±2.2 | Jul 2026 | Official leaderboard | |
| 41 | | 27.6% ±2.2 | Jul 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.2 | 71.3% | Nov 2026 | Official leaderboard | |
| 2 | 70.9% | Nov 2026 | Lab model card | ||
| 3 | Claude Sonnet 5.5 | 70.8% | Sep 2026 | Official leaderboard | |
| 4 | 70.5% | Oct 2026 | Official leaderboard | ||
| 5 | Claude Opus 5.5 | 70.1% | Sep 2026 | Official leaderboard | |
| 6 | 69.4% | Sep 2026 | Official leaderboard | ||
| 7 | 68.5% | Nov 2026 | Official leaderboard | ||
| 8 | GPT-6.2 Astra | 67.7% | Nov 2026 | Official leaderboard | |
| 9 | 66.8% | Oct 2026 | Official leaderboard | ||
| 10 | GPT-6.2 Sol | 66.1% | Nov 2026 | Official leaderboard | |
| 11 | GPT-6 Astra | 65% | Sep 2026 | Official leaderboard | |
| 12 | 64.9% | Oct 2026 | Official leaderboard | ||
| 13 | GPT-6.1 Sol | 63.9% | Sep 2026 | Official leaderboard | |
| 14 | 63.2% | Nov 2026 | Official leaderboard | ||
| 15 | Kimi K3.1 Pro | 62.5% | Oct 2026 | Official leaderboard | |
| 16 | 61.3% | Oct 2026 | Official leaderboard | ||
| 17 | GPT-6.1 Terra | 60.5% | Oct 2026 | Official leaderboard | |
| 18 | 60.5% | Nov 2026 | Official leaderboard | ||
| 19 | GLM-5.3 | 59.9% | Aug 2026 | Official leaderboard | |
| 20 | 59.4% | Nov 2026 | Official leaderboard | ||
| 21 | 59% | Sep 2026 | Official leaderboard | ||
| 22 | Claude Haiku 5.5 | 58.7% | Oct 2026 | Official leaderboard | |
| 23 | Grok 4.7 | 58.6% | Sep 2026 | Official leaderboard | |
| 24 | MiMo-V2.6 Pro | 57.8% | Sep 2026 | Official leaderboard | |
| 25 | 56.5% | Oct 2026 | Official leaderboard | ||
| 26 | 56.1% | Nov 2026 | Lab model card | ||
| 27 | 56% | Sep 2026 | Official leaderboard | ||
| 28 | MiMo-V2.6 Flash | 54.8% | Sep 2026 | Official leaderboard | |
| 29 | 54.8% | Sep 2026 | Official leaderboard | ||
| 30 | 53.8% | Oct 2026 | Official leaderboard | ||
| 31 | 53.2% | Aug 2026 | Official leaderboard | ||
| 32 | 53% | Aug 2026 | Official leaderboard | ||
| 33 | Kimi K3 | 53% | Jul 2026 | Official leaderboard | |
| 34 | GPT-6 Luna | 52.3% | Sep 2026 | Official leaderboard | |
| 35 | GLM-5.3-Flash | 50.9% | Aug 2026 | Official leaderboard | |
| 36 | 48.6% | Oct 2026 | Official leaderboard | ||
| 37 | 46.5% | Nov 2026 | Lab model card | ||
| 38 | Mercury 3 | 43.7% | Oct 2026 | Official leaderboard | |
| 39 | Beam 1.0 | 43.4% | Oct 2026 | Official leaderboard | |
| 40 | 29.8% | Oct 2026 | Official leaderboard | ||
| 41 | 29% | Jul 2026 | Official leaderboard | ||
| 42 | 27.6% | Jul 2026 | Official leaderboard |
Labs report scores for 4 models in their cards. Switch the scores above to rank them together.
Accuracy against latency
The Vals scatter chart with its x axis switched from Cost to Latency: mean time per test against accuracy, on a log scale. The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.
| Model | Setting | Accuracy | Latency (mean per test) |
|---|---|---|---|
| Claude Fable 5.2 | 71.3% | 2,622 s | |
| 70.9% | 1,885 s | ||
| Claude Sonnet 5.5 | 70.9% | 5,159 s | |
| 70.5% | 2,865 s | ||
| Claude Opus 5.5 | 70.1% | 5,071 s | |
| 69.4% | 2,698 s | ||
| 68.5% | 1,925 s | ||
| GPT-6.2 Astra | 67.7% | 3,136 s | |
| 66.8% | 3,559 s | ||
| GPT-6.2 Sol | 66.1% | 2,507 s | |
| GPT-6 Astra | 65% | 2,019 s | |
| 64.9% | 2,124 s | ||
| GPT-6.1 Sol | 63.9% | 2,664 s | |
| 63.2% | 3,880 s | ||
| Kimi K3.1 Pro | 62.5% | 3,817 s | |
| 61.3% | 2,395 s | ||
| GPT-6.1 Terra | 60.5% | 2,383 s | |
| 60.5% | 902.37 s | ||
| GLM-5.3 | 59.9% | 3,864 s | |
| 59.4% | 3,092 s | ||
| 59.1% | 6,346 s | ||
| Claude Haiku 5.5 | 58.7% | 2,997 s | |
| Grok 4.7 | 58.6% | 2,014 s | |
| MiMo-V2.6 Pro | 57.8% | 4,356 s | |
| 56.5% | 2,868 s | ||
| 56.1% | 3,035 s | ||
| 56% | 2,159 s | ||
| MiMo-V2.6 Flash | 54.8% | 4,028 s | |
| 54.8% | 3,929 s | ||
| 53.8% | 2,598 s | ||
| 53.2% | 3,563 s | ||
| 53% | 3,483 s | ||
| Kimi K3 | 53% | 4,496 s | |
| GPT-6 Luna | 52.3% | 1,943 s | |
| GLM-5.3-Flash | 50.9% | 3,831 s | |
| Hy4 Flash | 50.8% | 1,019 s | |
| 48.6% | 4,925 s | ||
| Mercury 3 | 43.7% | 1,326 s | |
| Beam 1.0 | 43.4% | 446.56 s | |
| 29.8% | 514.01 s | ||
| 29% | 1,033 s | ||
| 27.6% | 986.44 s |
Accuracy against latency
The Vals scatter chart with its x axis switched from Cost to Latency: mean time per test against accuracy, on a log scale. The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.
| Model | Setting | Accuracy | Latency (mean per test) |
|---|---|---|---|
| Claude Fable 5.2 | 71.3% | 2,622 s | |
| 70.9% | 1,885 s | ||
| Claude Sonnet 5.5 | 70.9% | 5,159 s | |
| 70.5% | 2,865 s | ||
| Claude Opus 5.5 | 70.1% | 5,071 s | |
| 69.4% | 2,698 s | ||
| 68.5% | 1,925 s | ||
| GPT-6.2 Astra | 67.7% | 3,136 s | |
| 66.8% | 3,559 s | ||
| GPT-6.2 Sol | 66.1% | 2,507 s | |
| GPT-6 Astra | 65% | 2,019 s | |
| 64.9% | 2,124 s | ||
| GPT-6.1 Sol | 63.9% | 2,664 s | |
| 63.2% | 3,880 s | ||
| Kimi K3.1 Pro | 62.5% | 3,817 s | |
| 61.3% | 2,395 s | ||
| GPT-6.1 Terra | 60.5% | 2,383 s | |
| 60.5% | 902.37 s | ||
| GLM-5.3 | 59.9% | 3,864 s | |
| 59.4% | 3,092 s | ||
| 59.1% | 6,346 s | ||
| Claude Haiku 5.5 | 58.7% | 2,997 s | |
| Grok 4.7 | 58.6% | 2,014 s | |
| MiMo-V2.6 Pro | 57.8% | 4,356 s | |
| 56.5% | 2,868 s | ||
| 56.1% | 3,035 s | ||
| 56% | 2,159 s | ||
| MiMo-V2.6 Flash | 54.8% | 4,028 s | |
| 54.8% | 3,929 s | ||
| 53.8% | 2,598 s | ||
| 53.2% | 3,563 s | ||
| 53% | 3,483 s | ||
| Kimi K3 | 53% | 4,496 s | |
| GPT-6 Luna | 52.3% | 1,943 s | |
| GLM-5.3-Flash | 50.9% | 3,831 s | |
| 48.6% | 4,925 s | ||
| Mercury 3 | 43.7% | 1,326 s | |
| Beam 1.0 | 43.4% | 446.56 s | |
| 29.8% | 514.01 s | ||
| 29% | 1,033 s | ||
| 27.6% | 986.44 s |
The best score, 71.3%, costs $18 a task
Runs on the cost frontier score higher than any run that's cheaper. Muse Wonder Full comes within 4.5 points of the best for $6.81 a task, 3 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official Vals Index v2.2 leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Fable 5.2 | 71.3% | $18 | 197,828 | ||
| 70.9% | $7.40 | 216,039 | |||
| Claude Sonnet 5.5 | 70.8% | $16 | 594,550 | ||
| 70.5% | $11 | 205,620 | |||
| Claude Opus 5.5 | 70.1% | $25 | 455,040 | ||
| 69.4% | $13 | 159,229 | |||
| 68.5% | $9.84 | 336,849 | |||
| GPT-6.2 Astra | 67.7% | $11 | 90,655 | ||
| 66.8% | $6.81 | 103,433 | |||
| GPT-6.2 Sol | 66.1% | $3.18 | 102,959 | ||
| GPT-6 Astra | 65% | $21 | 99,102 | ||
| 64.9% | $11 | 115,812 | |||
| GPT-6.1 Sol | 63.9% | $3.61 | 112,502 | ||
| 63.2% | $9.33 | 192,550 | |||
| Kimi K3.1 Pro | 62.5% | $6.44 | 159,072 | ||
| 61.3% | $0.66 | 258,045 | |||
| GPT-6.1 Terra | 60.5% | $2.94 | 157,426 | ||
| 60.5% | $0.15 | 79,013 | |||
| GLM-5.3 | 59.9% | $8.52 | 202,266 | ||
| 59.4% | $1.72 | 238,203 | |||
| 59% | $8.73 | 231,724 | |||
| Claude Haiku 5.5 | 58.7% | $3.17 | 570,127 | ||
| Grok 4.7 | 58.6% | $12 | 124,146 | ||
| MiMo-V2.6 Pro | 57.8% | $0.43 | 147,277 | ||
| 56.5% | $3.72 | 122,413 | |||
| 56.1% | $3.51 | 281,311 | |||
| 56% | $5.03 | 130,206 | |||
| MiMo-V2.6 Flash | 54.8% | $0.22 | 172,167 | ||
| 54.8% | $2.73 | 159,796 | |||
| 53.8% | $0.66 | 255,285 | |||
| 53.2% | $1.57 | 160,621 | |||
| 53% | $2.50 | 169,366 | |||
| Kimi K3 | 53% | $7.17 | 107,342 | ||
| GPT-6 Luna | 52.3% | $0.45 | 170,502 | ||
| GLM-5.3-Flash | 50.9% | $2.05 | 203,647 | ||
| 48.6% | $4.72 | 65,357 | |||
| Mercury 3 | 43.7% | $0.48 | 117,494 | ||
| Beam 1.0 | 43.4% | 41,553 | |||
| 29.8% | $0.63 | 96,498 | |||
| 29% | $1.85 | 64,607 | |||
| 27.6% | $0.40 | 55,978 |
The best score, 71.3%, costs $18 a task
Runs on the cost frontier score higher than any run that's cheaper. Muse Wonder Full comes within 4.5 points of the best for $6.81 a task, 3 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official Vals Index v2.2 leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Fable 5.2 | 71.3% | $18 | 197,828 | ||
| 70.9% | $7.40 | 216,039 | |||
| Claude Sonnet 5.5 | 70.8% | $16 | 594,550 | ||
| 70.5% | $11 | 205,620 | |||
| Claude Opus 5.5 | 70.1% | $25 | 455,040 | ||
| 69.4% | $13 | 159,229 | |||
| 68.5% | $9.84 | 336,849 | |||
| GPT-6.2 Astra | 67.7% | $11 | 90,655 | ||
| 66.8% | $6.81 | 103,433 | |||
| GPT-6.2 Sol | 66.1% | $3.18 | 102,959 | ||
| GPT-6 Astra | 65% | $21 | 99,102 | ||
| 64.9% | $11 | 115,812 | |||
| GPT-6.1 Sol | 63.9% | $3.61 | 112,502 | ||
| 63.2% | $9.33 | 192,550 | |||
| Kimi K3.1 Pro | 62.5% | $6.44 | 159,072 | ||
| 61.3% | $0.66 | 258,045 | |||
| GPT-6.1 Terra | 60.5% | $2.94 | 157,426 | ||
| 60.5% | $0.15 | 79,013 | |||
| GLM-5.3 | 59.9% | $8.52 | 202,266 | ||
| 59.4% | $1.72 | 238,203 | |||
| 59% | $8.73 | 231,724 | |||
| Claude Haiku 5.5 | 58.7% | $3.17 | 570,127 | ||
| Grok 4.7 | 58.6% | $12 | 124,146 | ||
| MiMo-V2.6 Pro | 57.8% | $0.43 | 147,277 | ||
| 56.5% | $3.72 | 122,413 | |||
| 56.1% | $3.51 | 281,311 | |||
| 56% | $5.03 | 130,206 | |||
| MiMo-V2.6 Flash | 54.8% | $0.22 | 172,167 | ||
| 54.8% | $2.73 | 159,796 | |||
| 53.8% | $0.66 | 255,285 | |||
| 53.2% | $1.57 | 160,621 | |||
| 53% | $2.50 | 169,366 | |||
| Kimi K3 | 53% | $7.17 | 107,342 | ||
| GPT-6 Luna | 52.3% | $0.45 | 170,502 | ||
| GLM-5.3-Flash | 50.9% | $2.05 | 203,647 | ||
| 48.6% | $4.72 | 65,357 | |||
| Mercury 3 | 43.7% | $0.48 | 117,494 | ||
| Beam 1.0 | 43.4% | 41,553 | |||
| 29.8% | $0.63 | 96,498 | |||
| 29% | $1.85 | 64,607 | |||
| 27.6% | $0.40 | 55,978 |
2 models have held number one on the official leaderboard since its release in October 2026 2 models have held number one with claims included since its release in October 2026
Lab claims count from the day the card came out, independent runs from the model’s release. We draw one row each for the benchmark’s own leaderboard and what labs claim in their cards.
Sources: Official Vals Index v2.2 leaderboard and labs’ model cards
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official Vals Index v2.2 leaderboard and labs’ model cards
2 labs put it in a launch post in the last six months
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out. Google DeepMind accounts for 3 of the 6 releases that named it since 2024.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Nov 20, 2026 | 46.5 | Vals Index (v2.2) | |
| Nov 18, 2026 | 70.9 | Vals Index v2.2 | |
| Nov 5, 2026 | 56.1 | Vals Index (v2.2) | |
| Oct 28, 2026 | 70.4 | Vals Index v2.2 |
3 system cards report it, from 2 labs
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Nov 20, 2026 | | 46.5 | Vals Index (v2.2) | Capabilities |
| Nov 18, 2026 | | 70.9 | Vals Index v2.2 (results table, p.4) | Capabilities |
| Nov 10, 2026 | | 70.4 | Vals Index v2.2 (results table) | Capabilities |
3 lab claims next to the leaderboard
Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 3 of them match, which usually means one side copied the other. Every benchmark.
| Model | Lab says | Board says | Gap |
|---|---|---|---|
| | 70.4% Vals Index v2.2 | 70.5% Leaderboard | Same |
| | 70.9% Vals Index v2.2 | 70.9% Leaderboard | Same |
| | 56.1% Vals Index (v2.2) | 56.1% Leaderboard | Same |
Versions
We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.
Source: Official leaderboards
More in Economic work
- JobBench In use 130 tasks from 35 occupations workers most want delegated. Agent works through messy reference files, graded by fact-anchored binary rubrics. GLM-5.3 61.4%
- GDPval In use Real work tasks from 44 occupations with reference files. Experts blindly compare model deliverables with expert work. Metric is win-or-tie rate.
Seed2.1 Pro 87.9%
- GDPval-AA v2.1 In use Agents with shell and web access complete 220 GDPval gold tasks from 44 occupations. Blind pairwise comparisons give Elo ratings. Claude Opus 5.5 1,846
- AA-Briefcase v1.1 In use Version 1.1 of Artificial Analysis's multi-hour office work evaluation, with Elo ratings fitted by Crowd-BT. Claude Opus 5.5 1,822
- Agents' Last Exam v1.1 In use Agents complete 122 public long-horizon professional workflow tasks across 55 sub-industries. Deterministic graders check outcomes against hidden references. GPT-6.2 Astra 47.5%
- CoWorkBench In use Agent completes long-horizon productivity tasks across computer science, finance, law and medicine. Qwen in-house scoring (method unpublished). Claude Fable 5 75.9%
Data audit
All 12 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 5 pass
- Pass Independent runs Scores from the official leaderboard (42 entries), launch posts (4 scores) and system cards (3 scores).
- Pass Models scored 42 models we track, plus 1 other entry on its leaderboard.
- Pass Newest score The newest is from November 2026, for Inkling 2 Mini.
- Pass Frontier models 9 of the top 10 have a score, led by GPT-6.2 Astra (#1).
- Pass Headroom The best is 71.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on vals.ai: 41 rows for models we track and 1 other entry at the last read.
- Pass Last read November 19th, 2026.
- Pass Read worked The last read worked.
Consistency 2 pass
- Pass Lab claims All 3 pairs agree within 10 points.
- Pass Known issues No published audit found problems.