Excel Modeling Benchmark v1.1
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 66%.
Agents build the same 103 Excel financial modeling tasks as EMB v1.0, with the Scratch rubric judge changed to GPT-6 Luna.
Vals says v1.1 scores are not directly comparable with v1.0. Part of Vals Index v2.2 from October 19th, 2026. The board had 37 models on October 29th, 2026.
- Made by
- Vals AI
- Released
- October 2026
- Kind
- Finance
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Agent task
- Tasks
- Kept private
- Measures
- Capability
- Subject
- Economics and business
- Language
- English
- Interaction
- Agentic
- Environment
- Microsoft Excel
- Items from
- Another benchmark
- Refresh
- New versions replace it
- Run by
- A host
- Based on
- Excel Modeling Benchmark
- 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 20th, 2026
Claude Fable 5.2 leads with 77.4% Claude Fable 5.2 leads with 77.4%
Best score per entry from the benchmark's own leaderboard, read on November 20th, 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 77.4%, 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.
- 77.4 Claude Fable 5.2
- 76.7 Claude Fable 5.1
- 76.5
Gemini 4 Carbon
- 76.5
Gemini 4 Neon
- 76.0 GPT-6.2 Astra
- 75.9 Claude Sonnet 5.5
- 75.8 Claude Opus 5.5
- 75.8
Gemini 4 Hydrogen
- 75.0
Muse Wonder Full
- 74.8
Gemini 4 Argon
- 74.3 GPT-6.2 Sol
- 73.3 GPT-6.1 Terra
- 72.9
Gemini 3.8 Flash
- 72.7 GPT-6 Astra
- 72.5
Muse Wonder
- 72.2
Muse Ember
- 72.0
Qwen3.8 Max (0902)
- 71.5 Grok 4.7
- 71.3 Kimi K3
- 71.1 GPT-6.1 Sol
- 70.8
Qwen4-Max
- 70.0 Kimi K3.1 Pro
- 70.0 GPT-6 Luna
- 69.5
Step 5 Preview
- 69.5
Inkling 2 Small
- 69.2
DeepSeek V4.1 Flash 1017
- 69.1 GLM-5.3
- 69.0
Mistral Large 4 Preview
- 69.0
Tencent Hy4 preview
- 68.9 MiMo-V2.6 Flash
- 68.7
Mistral Large 4
- 67.8
MiniMax-M3.1-Flash
- 67.8
DeepSeek V4.1 Flash
- 67.3 MiMo-V2.6 Pro
- 66.3 GLM-5.3-Flash
- 66.2
Tencent Hy4
- 66.0
Qwen 3.8 Max
- 65.5 Claude Haiku 5.5
- 65.1
DeepSeek V4 Pro 0813
- 64.7 Beam 1.0
- 63.0 Hy4 Flash
- 62.0
Muse Spark Open
- 59.8
MiniMax-M3
- 57.9 Mercury 3
- 52.8
Nemotron 3.5 Super VL
- 41.0
Inkling
- 40.8
Inkling-Small
- 1 Claude Fable 5.2 77.4%
- 2 Claude Fable 5.1 76.7%
- 3
Gemini 4 Carbon 76.5%
- 4
Gemini 4 Neon 76.5%
- 5 GPT-6.2 Astra 76%
- 6 Claude Sonnet 5.5 75.9%
- 7 Claude Opus 5.5 75.8%
- 8
Gemini 4 Hydrogen 75.8%
- 9
Muse Wonder Full 75%
- 10
Gemini 4 Argon 74.8%
- 11 GPT-6.2 Sol 74.3%
- 12 GPT-6.1 Terra 73.3%
- 13
Gemini 3.8 Flash 72.9%
- 14 GPT-6 Astra 72.7%
- 15
Muse Wonder 72.5%
- 16
Muse Ember 72.2%
- 17
Qwen3.8 Max (0902) 72%
- 18 Grok 4.7 71.5%
- 19 Kimi K3 71.3%
- 20 GPT-6.1 Sol 71.1%
- 21
Qwen4-Max 70.8%
- 22 Kimi K3.1 Pro 70%
- 23 GPT-6 Luna 70%
- 24
Step 5 Preview 69.5%
- 25
Inkling 2 Small 69.5%
- 26
DeepSeek V4.1 Flash 1017 69.2%
- 27 GLM-5.3 69.1%
- 28
Mistral Large 4 Preview 69%
- 29
Tencent Hy4 preview 69%
- 30 MiMo-V2.6 Flash 68.9%
- 31
Mistral Large 4 68.7%
- 32
MiniMax-M3.1-Flash 67.8%
- 33
DeepSeek V4.1 Flash 67.8%
- 34 MiMo-V2.6 Pro 67.3%
- 35 GLM-5.3-Flash 66.3%
- 36
Tencent Hy4 66.2%
- 37
Qwen 3.8 Max 66%
- 38 Claude Haiku 5.5 65.5%
- 39
DeepSeek V4 Pro 0813 65.1%
- 40 Beam 1.0 64.7%
- 41 Hy4 Flash 63%
- 42
Muse Spark Open 62%
- 43
MiniMax-M3 59.8%
- 44 Mercury 3 57.9%
- 45
Nemotron 3.5 Super VL 52.8%
- 46
Inkling 41%
- 47
Inkling-Small 40.8%
Source: Official Excel Modeling Benchmark v1.1 leaderboard
- 77.4 Claude Fable 5.2
- 76.7 Claude Fable 5.1
- 76.5
Gemini 4 Carbon
- 76.5
Gemini 4 Neon
- 76.0 GPT-6.2 Astra
- 75.9 Claude Sonnet 5.5
- 75.8 Claude Opus 5.5
- 75.8
Gemini 4 Hydrogen
- 75.0
Muse Wonder Full
- 74.8
Gemini 4 Argon
- 74.3 GPT-6.2 Sol
- 73.3 GPT-6.1 Terra
- 72.9
Gemini 3.8 Flash
- 72.7 GPT-6 Astra
- 72.5
Muse Wonder
- 72.2
Muse Ember
- 72.0
Qwen3.8 Max (0902)
- 71.5 Grok 4.7
- 71.3 Kimi K3
- 71.1 GPT-6.1 Sol
- 70.8
Qwen4-Max
- 70.0 Kimi K3.1 Pro
- 70.0 GPT-6 Luna
- 69.5
Step 5 Preview
- 69.5
Inkling 2 Small
- 69.2
DeepSeek V4.1 Flash 1017
- 69.1 GLM-5.3
- 69.0
Mistral Large 4 Preview
- 69.0
Tencent Hy4 preview
- 68.9 MiMo-V2.6 Flash
- 68.7
Mistral Large 4
- 67.8
MiniMax-M3.1-Flash
- 67.8
DeepSeek V4.1 Flash
- 67.3 MiMo-V2.6 Pro
- 66.3 GLM-5.3-Flash
- 66.2
Tencent Hy4
- 66.0
Qwen 3.8 Max
- 65.5 Claude Haiku 5.5
- 65.1
DeepSeek V4 Pro 0813
- 64.7 Beam 1.0
- 62.0
Muse Spark Open
- 59.8
MiniMax-M3
- 57.9 Mercury 3
- 52.8
Nemotron 3.5 Super VL
- 41.0
Inkling
- 40.8
Inkling-Small
- 1 Claude Fable 5.2 77.4%
- 2 Claude Fable 5.1 76.7%
- 3
Gemini 4 Carbon 76.5%
- 4
Gemini 4 Neon 76.5%
- 5 GPT-6.2 Astra 76%
- 6 Claude Sonnet 5.5 75.9%
- 7 Claude Opus 5.5 75.8%
- 8
Gemini 4 Hydrogen 75.8%
- 9
Muse Wonder Full 75%
- 10
Gemini 4 Argon 74.8%
- 11 GPT-6.2 Sol 74.3%
- 12 GPT-6.1 Terra 73.3%
- 13
Gemini 3.8 Flash 72.9%
- 14 GPT-6 Astra 72.7%
- 15
Muse Wonder 72.5%
- 16
Muse Ember 72.2%
- 17
Qwen3.8 Max (0902) 72%
- 18 Grok 4.7 71.5%
- 19 Kimi K3 71.3%
- 20 GPT-6.1 Sol 71.1%
- 21
Qwen4-Max 70.8%
- 22 Kimi K3.1 Pro 70%
- 23 GPT-6 Luna 70%
- 24
Step 5 Preview 69.5%
- 25
Inkling 2 Small 69.5%
- 26
DeepSeek V4.1 Flash 1017 69.2%
- 27 GLM-5.3 69.1%
- 28
Mistral Large 4 Preview 69%
- 29
Tencent Hy4 preview 69%
- 30 MiMo-V2.6 Flash 68.9%
- 31
Mistral Large 4 68.7%
- 32
MiniMax-M3.1-Flash 67.8%
- 33
DeepSeek V4.1 Flash 67.8%
- 34 MiMo-V2.6 Pro 67.3%
- 35 GLM-5.3-Flash 66.3%
- 36
Tencent Hy4 66.2%
- 37
Qwen 3.8 Max 66%
- 38 Claude Haiku 5.5 65.5%
- 39
DeepSeek V4 Pro 0813 65.1%
- 40 Beam 1.0 64.7%
- 41
Muse Spark Open 62%
- 42
MiniMax-M3 59.8%
- 43 Mercury 3 57.9%
- 44
Nemotron 3.5 Super VL 52.8%
- 45
Inkling 41%
- 46
Inkling-Small 40.8%
Source: Official Excel Modeling Benchmark v1.1 leaderboard
- 77.4 Claude Fable 5.2
- 76.7 Claude Fable 5.1
- 76.5
Gemini 4 Carbon
- 76.5
Gemini 4 Neon
- 76.0 GPT-6.2 Astra
- 75.9 Claude Sonnet 5.5
- 75.8 Claude Opus 5.5
- 75.8
Gemini 4 Hydrogen
- 75.0
Muse Wonder Full
- 74.8
Gemini 4 Argon
- 74.3 GPT-6.2 Sol
- 73.3 GPT-6.1 Terra
- 72.9
Gemini 3.8 Flash
- 72.7 GPT-6 Astra
- 72.5
Muse Wonder
- 72.2
Muse Ember
- 72.0
Qwen3.8 Max (0902)
- 71.5 Grok 4.7
- 71.3 Kimi K3
- 71.1 GPT-6.1 Sol
- 70.8
Qwen4-Max
- 70.0 Kimi K3.1 Pro
- 70.0 GPT-6 Luna
- 69.5
Step 5 Preview
- 69.5
Inkling 2 Small
- 69.2
DeepSeek V4.1 Flash 1017
- 69.1 GLM-5.3
- 69.0
Mistral Large 4 Preview
- 69.0
Tencent Hy4 preview
- 68.9 MiMo-V2.6 Flash
- 68.7
Mistral Large 4
- 67.8
MiniMax-M3.1-Flash
- 67.8
DeepSeek V4.1 Flash
- 67.3 MiMo-V2.6 Pro
- 66.3 GLM-5.3-Flash
- 66.2
Tencent Hy4
- 66.0
Inkling 2 Mini
- 66.0
Qwen 3.8 Max
- 65.5 Claude Haiku 5.5
- 65.1
DeepSeek V4 Pro 0813
- 64.7 Beam 1.0
- 62.0
Muse Spark Open
- 59.8
MiniMax-M3
- 57.9 Mercury 3
- 52.8
Nemotron 3.5 Super VL
- 41.0
Inkling
- 40.8
Inkling-Small
- 1 Claude Fable 5.2 77.4%
- 2 Claude Fable 5.1 76.7%
- 3
Gemini 4 Carbon 76.5%
- 4
Gemini 4 Neon 76.5%
- 5 GPT-6.2 Astra 76%
- 6 Claude Sonnet 5.5 75.9%
- 7 Claude Opus 5.5 75.8%
- 8
Gemini 4 Hydrogen 75.8%
- 9
Muse Wonder Full 75%
- 10
Gemini 4 Argon 74.8%
- 11 GPT-6.2 Sol 74.3%
- 12 GPT-6.1 Terra 73.3%
- 13
Gemini 3.8 Flash 72.9%
- 14 GPT-6 Astra 72.7%
- 15
Muse Wonder 72.5%
- 16
Muse Ember 72.2%
- 17
Qwen3.8 Max (0902) 72%
- 18 Grok 4.7 71.5%
- 19 Kimi K3 71.3%
- 20 GPT-6.1 Sol 71.1%
- 21
Qwen4-Max 70.8%
- 22 Kimi K3.1 Pro 70%
- 23 GPT-6 Luna 70%
- 24
Step 5 Preview 69.5%
- 25
Inkling 2 Small 69.5%
- 26
DeepSeek V4.1 Flash 1017 69.2%
- 27 GLM-5.3 69.1%
- 28
Mistral Large 4 Preview 69%
- 29
Tencent Hy4 preview 69%
- 30 MiMo-V2.6 Flash 68.9%
- 31
Mistral Large 4 68.7%
- 32
MiniMax-M3.1-Flash 67.8%
- 33
DeepSeek V4.1 Flash 67.8%
- 34 MiMo-V2.6 Pro 67.3%
- 35 GLM-5.3-Flash 66.3%
- 36
Tencent Hy4 66.2%
- 37
Inkling 2 Mini 66%
- 38
Qwen 3.8 Max 66%
- 39 Claude Haiku 5.5 65.5%
- 40
DeepSeek V4 Pro 0813 65.1%
- 41 Beam 1.0 64.7%
- 42
Muse Spark Open 62%
- 43
MiniMax-M3 59.8%
- 44 Mercury 3 57.9%
- 45
Nemotron 3.5 Super VL 52.8%
- 46
Inkling 41%
- 47
Inkling-Small 40.8%
Sources: Official Excel Modeling Benchmark v1.1 leaderboard and labs’ model cards
| # | Entry | Score ± 95% CI | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.2 | 77.4% ±4.3 | Nov 2026 | Official leaderboard | |
| 2 | Claude Fable 5.1 | 76.7% ±4.2 | Sep 2026 | Official leaderboard | |
| 3 | | 76.5% ±4.3 | Oct 2026 | Official leaderboard | |
| 4 | | 76.5% ±4 | Nov 2026 | Official leaderboard | |
| 5 | GPT-6.2 Astra | 76% ±4.4 | Nov 2026 | Official leaderboard | |
| 6 | Claude Sonnet 5.5 | 75.9% ±4.8 | Sep 2026 | Official leaderboard | |
| 7 | Claude Opus 5.5 | 75.8% ±4.7 | Sep 2026 | Official leaderboard | |
| 8 | | 75.8% ±4 | Nov 2026 | Official leaderboard | |
| 9 | | 75% ±4.2 | Oct 2026 | Official leaderboard | |
| 10 | | 74.8% ±4.9 | Sep 2026 | Official leaderboard | |
| 11 | GPT-6.2 Sol | 74.3% ±4.4 | Nov 2026 | Official leaderboard | |
| 12 | GPT-6.1 Terra | 73.3% ±4.4 | Oct 2026 | Official leaderboard | |
| 13 | | 72.9% ±4.8 | Sep 2026 | Official leaderboard | |
| 14 | GPT-6 Astra | 72.7% ±4.5 | Sep 2026 | Official leaderboard | |
| 15 | | 72.5% ±4.7 | Oct 2026 | Official leaderboard | |
| 16 | | 72.2% ±4.5 | Nov 2026 | Official leaderboard | |
| 17 | | 72% ±4.7 | Sep 2026 | Official leaderboard | |
| 18 | Grok 4.7 | 71.5% ±4.6 | Sep 2026 | Official leaderboard | |
| 19 | Kimi K3 | 71.3% ±4.5 | Jul 2026 | Official leaderboard | |
| 20 | GPT-6.1 Sol | 71.1% ±5.4 | Sep 2026 | Official leaderboard | |
| 21 | | 70.8% ±4.6 | Nov 2026 | Official leaderboard | |
| 22 | Kimi K3.1 Pro | 70% ±5.2 | Oct 2026 | Official leaderboard | |
| 23 | GPT-6 Luna | 70% ±5 | Sep 2026 | Official leaderboard | |
| 24 | | 69.5% ±4.9 | Sep 2026 | Official leaderboard | |
| 25 | | 69.5% ±4.9 | Nov 2026 | Official leaderboard | |
| 26 | | 69.2% ±4.7 | Oct 2026 | Official leaderboard | |
| 27 | GLM-5.3 | 69.1% ±5.2 | Aug 2026 | Official leaderboard | |
| 28 | | 69% ±4.6 | Oct 2026 | Official leaderboard | |
| 29 | | 69% ±4.7 | Aug 2026 | Official leaderboard | |
| 30 | MiMo-V2.6 Flash | 68.9% ±4.4 | Sep 2026 | Official leaderboard | |
| 31 | | 68.7% ±4.8 | Oct 2026 | Official leaderboard | |
| 32 | | 67.8% ±4.5 | Oct 2026 | Official leaderboard | |
| 33 | | 67.8% ±5 | Sep 2026 | Official leaderboard | |
| 34 | MiMo-V2.6 Pro | 67.3% ±5.7 | Sep 2026 | Official leaderboard | |
| 35 | GLM-5.3-Flash | 66.3% ±5.3 | Aug 2026 | Official leaderboard | |
| 36 | | 66.2% ±5.2 | Nov 2026 | Official leaderboard | |
| 37 | | 66% ±5.3 | Aug 2026 | Official leaderboard | |
| 38 | Claude Haiku 5.5 | 65.5% ±7.2 | Oct 2026 | Official leaderboard | |
| 39 | | 65.1% ±4.6 | Aug 2026 | Official leaderboard | |
| 40 | Beam 1.0 | 64.7% ±4.4 | Oct 2026 | Official leaderboard | |
| 41 | Hy4 Flash | 63% ±4.4 | Official leaderboard | ||
| 42 | | 62% ±5.3 | Oct 2026 | Official leaderboard | |
| 43 | | 59.8% ±5 | Jun 2026 | Official leaderboard | |
| 44 | Mercury 3 | 57.9% ±5.7 | Oct 2026 | Official leaderboard | |
| 45 | | 52.8% ±5.5 | Oct 2026 | Official leaderboard | |
| 46 | | 41% ±5.8 | Jul 2026 | Official leaderboard | |
| 47 | | 40.8% ±6.3 | Jul 2026 | Official leaderboard |
| # | Model | Score ± 95% CI | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.2 | 77.4% ±4.3 | Nov 2026 | Official leaderboard | |
| 2 | Claude Fable 5.1 | 76.7% ±4.2 | Sep 2026 | Official leaderboard | |
| 3 | | 76.5% ±4.3 | Oct 2026 | Official leaderboard | |
| 4 | | 76.5% ±4 | Nov 2026 | Official leaderboard | |
| 5 | GPT-6.2 Astra | 76% ±4.4 | Nov 2026 | Official leaderboard | |
| 6 | Claude Sonnet 5.5 | 75.9% ±4.8 | Sep 2026 | Official leaderboard | |
| 7 | Claude Opus 5.5 | 75.8% ±4.7 | Sep 2026 | Official leaderboard | |
| 8 | | 75.8% ±4 | Nov 2026 | Official leaderboard | |
| 9 | | 75% ±4.2 | Oct 2026 | Official leaderboard | |
| 10 | | 74.8% ±4.9 | Sep 2026 | Official leaderboard | |
| 11 | GPT-6.2 Sol | 74.3% ±4.4 | Nov 2026 | Official leaderboard | |
| 12 | GPT-6.1 Terra | 73.3% ±4.4 | Oct 2026 | Official leaderboard | |
| 13 | | 72.9% ±4.8 | Sep 2026 | Official leaderboard | |
| 14 | GPT-6 Astra | 72.7% ±4.5 | Sep 2026 | Official leaderboard | |
| 15 | | 72.5% ±4.7 | Oct 2026 | Official leaderboard | |
| 16 | | 72.2% ±4.5 | Nov 2026 | Official leaderboard | |
| 17 | | 72% ±4.7 | Sep 2026 | Official leaderboard | |
| 18 | Grok 4.7 | 71.5% ±4.6 | Sep 2026 | Official leaderboard | |
| 19 | Kimi K3 | 71.3% ±4.5 | Jul 2026 | Official leaderboard | |
| 20 | GPT-6.1 Sol | 71.1% ±5.4 | Sep 2026 | Official leaderboard | |
| 21 | | 70.8% ±4.6 | Nov 2026 | Official leaderboard | |
| 22 | Kimi K3.1 Pro | 70% ±5.2 | Oct 2026 | Official leaderboard | |
| 23 | GPT-6 Luna | 70% ±5 | Sep 2026 | Official leaderboard | |
| 24 | | 69.5% ±4.9 | Sep 2026 | Official leaderboard | |
| 25 | | 69.5% ±4.9 | Nov 2026 | Official leaderboard | |
| 26 | | 69.2% ±4.7 | Oct 2026 | Official leaderboard | |
| 27 | GLM-5.3 | 69.1% ±5.2 | Aug 2026 | Official leaderboard | |
| 28 | | 69% ±4.6 | Oct 2026 | Official leaderboard | |
| 29 | | 69% ±4.7 | Aug 2026 | Official leaderboard | |
| 30 | MiMo-V2.6 Flash | 68.9% ±4.4 | Sep 2026 | Official leaderboard | |
| 31 | | 68.7% ±4.8 | Oct 2026 | Official leaderboard | |
| 32 | | 67.8% ±4.5 | Oct 2026 | Official leaderboard | |
| 33 | | 67.8% ±5 | Sep 2026 | Official leaderboard | |
| 34 | MiMo-V2.6 Pro | 67.3% ±5.7 | Sep 2026 | Official leaderboard | |
| 35 | GLM-5.3-Flash | 66.3% ±5.3 | Aug 2026 | Official leaderboard | |
| 36 | | 66.2% ±5.2 | Nov 2026 | Official leaderboard | |
| 37 | | 66% ±5.3 | Aug 2026 | Official leaderboard | |
| 38 | Claude Haiku 5.5 | 65.5% ±7.2 | Oct 2026 | Official leaderboard | |
| 39 | | 65.1% ±4.6 | Aug 2026 | Official leaderboard | |
| 40 | Beam 1.0 | 64.7% ±4.4 | Oct 2026 | Official leaderboard | |
| 41 | | 62% ±5.3 | Oct 2026 | Official leaderboard | |
| 42 | | 59.8% ±5 | Jun 2026 | Official leaderboard | |
| 43 | Mercury 3 | 57.9% ±5.7 | Oct 2026 | Official leaderboard | |
| 44 | | 52.8% ±5.5 | Oct 2026 | Official leaderboard | |
| 45 | | 41% ±5.8 | Jul 2026 | Official leaderboard | |
| 46 | | 40.8% ±6.3 | Jul 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.2 | 77.4% | Nov 2026 | Official leaderboard | |
| 2 | Claude Fable 5.1 | 76.7% | Sep 2026 | Official leaderboard | |
| 3 | 76.5% | Oct 2026 | Official leaderboard | ||
| 4 | 76.5% | Nov 2026 | Official leaderboard | ||
| 5 | GPT-6.2 Astra | 76% | Nov 2026 | Official leaderboard | |
| 6 | Claude Sonnet 5.5 | 75.9% | Sep 2026 | Official leaderboard | |
| 7 | Claude Opus 5.5 | 75.8% | Sep 2026 | Official leaderboard | |
| 8 | 75.8% | Nov 2026 | Official leaderboard | ||
| 9 | 75% | Oct 2026 | Official leaderboard | ||
| 10 | 74.8% | Sep 2026 | Official leaderboard | ||
| 11 | GPT-6.2 Sol | 74.3% | Nov 2026 | Official leaderboard | |
| 12 | GPT-6.1 Terra | 73.3% | Oct 2026 | Official leaderboard | |
| 13 | 72.9% | Sep 2026 | Official leaderboard | ||
| 14 | GPT-6 Astra | 72.7% | Sep 2026 | Official leaderboard | |
| 15 | 72.5% | Oct 2026 | Official leaderboard | ||
| 16 | 72.2% | Nov 2026 | Official leaderboard | ||
| 17 | 72% | Sep 2026 | Official leaderboard | ||
| 18 | Grok 4.7 | 71.5% | Sep 2026 | Official leaderboard | |
| 19 | Kimi K3 | 71.3% | Jul 2026 | Official leaderboard | |
| 20 | GPT-6.1 Sol | 71.1% | Sep 2026 | Official leaderboard | |
| 21 | 70.8% | Nov 2026 | Official leaderboard | ||
| 22 | Kimi K3.1 Pro | 70% | Oct 2026 | Official leaderboard | |
| 23 | GPT-6 Luna | 70% | Sep 2026 | Official leaderboard | |
| 24 | 69.5% | Sep 2026 | Official leaderboard | ||
| 25 | 69.5% | Nov 2026 | Official leaderboard | ||
| 26 | 69.2% | Oct 2026 | Official leaderboard | ||
| 27 | GLM-5.3 | 69.1% | Aug 2026 | Official leaderboard | |
| 28 | 69% | Oct 2026 | Official leaderboard | ||
| 29 | 69% | Aug 2026 | Official leaderboard | ||
| 30 | MiMo-V2.6 Flash | 68.9% | Sep 2026 | Official leaderboard | |
| 31 | 68.7% | Oct 2026 | Official leaderboard | ||
| 32 | 67.8% | Oct 2026 | Official leaderboard | ||
| 33 | 67.8% | Sep 2026 | Official leaderboard | ||
| 34 | MiMo-V2.6 Pro | 67.3% | Sep 2026 | Official leaderboard | |
| 35 | GLM-5.3-Flash | 66.3% | Aug 2026 | Official leaderboard | |
| 36 | 66.2% | Nov 2026 | Official leaderboard | ||
| 37 | 66% | Nov 2026 | Lab model card | ||
| 38 | 66% | Aug 2026 | Official leaderboard | ||
| 39 | Claude Haiku 5.5 | 65.5% | Oct 2026 | Official leaderboard | |
| 40 | 65.1% | Aug 2026 | Official leaderboard | ||
| 41 | Beam 1.0 | 64.7% | Oct 2026 | Official leaderboard | |
| 42 | 62% | Oct 2026 | Official leaderboard | ||
| 43 | 59.8% | Jun 2026 | Official leaderboard | ||
| 44 | Mercury 3 | 57.9% | Oct 2026 | Official leaderboard | |
| 45 | 52.8% | Oct 2026 | Official leaderboard | ||
| 46 | 41% | Jul 2026 | Official leaderboard | ||
| 47 | 40.8% | Jul 2026 | Official leaderboard |
Labs report scores for 2 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 | 77.4% | 979.09 s | |
| Claude Fable 5.1 | 76.7% | 1,772 s | |
| 76.5% | 1,649 s | ||
| 76.5% | 963.24 s | ||
| GPT-6.2 Astra | 76% | 1,286 s | |
| Claude Sonnet 5.5 | 75.9% | 2,205 s | |
| Claude Opus 5.5 | 75.8% | 2,106 s | |
| 75.8% | 662.89 s | ||
| 75% | 1,685 s | ||
| 74.8% | 2,306 s | ||
| GPT-6.2 Sol | 74.3% | 887.08 s | |
| GPT-6.1 Terra | 73.3% | 756.89 s | |
| 72.9% | 769.2 s | ||
| GPT-6 Astra | 72.7% | 804.28 s | |
| 72.5% | 1,034 s | ||
| 72.2% | 289.84 s | ||
| 72% | 3,193 s | ||
| Grok 4.7 | 71.5% | 2,097 s | |
| Kimi K3 | 71.3% | 741.42 s | |
| GPT-6.1 Sol | 71.1% | 1,108 s | |
| 70.8% | 970.57 s | ||
| Kimi K3.1 Pro | 70% | 1,283 s | |
| GPT-6 Luna | 70% | 1,041 s | |
| 69.6% | 2,615 s | ||
| 69.5% | 833.92 s | ||
| 69.2% | 1,972 s | ||
| GLM-5.3 | 69.1% | 2,172 s | |
| 69% | 4,905 s | ||
| 69% | 1,839 s | ||
| MiMo-V2.6 Flash | 68.9% | 1,522 s | |
| 68.7% | 1,387 s | ||
| 67.8% | 1,848 s | ||
| 67.8% | 780.46 s | ||
| MiMo-V2.6 Pro | 67.4% | 3,314 s | |
| GLM-5.3-Flash | 66.3% | 4,495 s | |
| 66.2% | 1,059 s | ||
| 66% | 3,467 s | ||
| Claude Haiku 5.5 | 65.5% | 1,196 s | |
| 65.1% | 2,247 s | ||
| Beam 1.0 | 64.7% | 1,204 s | |
| Hy4 Flash | 63% | 427.58 s | |
| 62% | 5,079 s | ||
| 59.8% | 1,299 s | ||
| Mercury 3 | 57.9% | 531.28 s | |
| 52.8% | 816.73 s | ||
| 41% | 1,582 s | ||
| 40.8% | 1,174 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 | 77.4% | 979.09 s | |
| Claude Fable 5.1 | 76.7% | 1,772 s | |
| 76.5% | 1,649 s | ||
| 76.5% | 963.24 s | ||
| GPT-6.2 Astra | 76% | 1,286 s | |
| Claude Sonnet 5.5 | 75.9% | 2,205 s | |
| Claude Opus 5.5 | 75.8% | 2,106 s | |
| 75.8% | 662.89 s | ||
| 75% | 1,685 s | ||
| 74.8% | 2,306 s | ||
| GPT-6.2 Sol | 74.3% | 887.08 s | |
| GPT-6.1 Terra | 73.3% | 756.89 s | |
| 72.9% | 769.2 s | ||
| GPT-6 Astra | 72.7% | 804.28 s | |
| 72.5% | 1,034 s | ||
| 72.2% | 289.84 s | ||
| 72% | 3,193 s | ||
| Grok 4.7 | 71.5% | 2,097 s | |
| Kimi K3 | 71.3% | 741.42 s | |
| GPT-6.1 Sol | 71.1% | 1,108 s | |
| 70.8% | 970.57 s | ||
| Kimi K3.1 Pro | 70% | 1,283 s | |
| GPT-6 Luna | 70% | 1,041 s | |
| 69.6% | 2,615 s | ||
| 69.5% | 833.92 s | ||
| 69.2% | 1,972 s | ||
| GLM-5.3 | 69.1% | 2,172 s | |
| 69% | 4,905 s | ||
| 69% | 1,839 s | ||
| MiMo-V2.6 Flash | 68.9% | 1,522 s | |
| 68.7% | 1,387 s | ||
| 67.8% | 1,848 s | ||
| 67.8% | 780.46 s | ||
| MiMo-V2.6 Pro | 67.4% | 3,314 s | |
| GLM-5.3-Flash | 66.3% | 4,495 s | |
| 66.2% | 1,059 s | ||
| 66% | 3,467 s | ||
| Claude Haiku 5.5 | 65.5% | 1,196 s | |
| 65.1% | 2,247 s | ||
| Beam 1.0 | 64.7% | 1,204 s | |
| 62% | 5,079 s | ||
| 59.8% | 1,299 s | ||
| Mercury 3 | 57.9% | 531.28 s | |
| 52.8% | 816.73 s | ||
| 41% | 1,582 s | ||
| 40.8% | 1,174 s |
The best score, 77.4%, costs $6.67 a task
Runs on the cost frontier score higher than any run that's cheaper. GPT-6.1 Terra comes within 4 points of the best for $0.56 a task, 12 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official Excel Modeling Benchmark v1.1 leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Fable 5.2 | 77.4% | $6.67 | 89,316 | ||
| Claude Fable 5.1 | 76.7% | $16 | 122,541 | ||
| 76.5% | $5.76 | 128,574 | |||
| 76.5% | $3.82 | 128,555 | |||
| GPT-6.2 Astra | 76% | $2.80 | 34,759 | ||
| Claude Sonnet 5.5 | 75.9% | $6.53 | 287,535 | ||
| Claude Opus 5.5 | 75.8% | $9.33 | 232,398 | ||
| 75.8% | $3.17 | 143,883 | |||
| 75% | $4.58 | 81,668 | |||
| 74.8% | $12 | 139,780 | |||
| GPT-6.2 Sol | 74.3% | $0.84 | 38,838 | ||
| GPT-6.1 Terra | 73.3% | $0.56 | 56,429 | ||
| 72.9% | $8.24 | 212,969 | |||
| GPT-6 Astra | 72.7% | $5.83 | 54,340 | ||
| 72.5% | $5.60 | 79,695 | |||
| 72.2% | $0.09 | 70,585 | |||
| 72% | $4.43 | 142,004 | |||
| Grok 4.7 | 71.5% | $6.48 | 152,252 | ||
| Kimi K3 | 71.3% | $3.07 | 95,082 | ||
| GPT-6.1 Sol | 71.1% | $1.14 | 59,382 | ||
| 70.8% | $1.00 | 79,218 | |||
| Kimi K3.1 Pro | 70% | $1.59 | 63,212 | ||
| GPT-6 Luna | 70% | $0.14 | 107,914 | ||
| 69.5% | $1.33 | 144,151 | |||
| 69.5% | $0.53 | 134,164 | |||
| 69.2% | $0.33 | 158,012 | |||
| GLM-5.3 | 69.1% | $3.79 | 179,978 | ||
| 69% | $2.47 | 170,078 | |||
| 69% | $0.79 | 102,269 | |||
| MiMo-V2.6 Flash | 68.9% | $0.11 | 157,412 | ||
| 68.7% | $0.83 | 89,247 | |||
| 67.8% | $0.27 | 139,084 | |||
| 67.8% | $0.23 | 130,189 | |||
| MiMo-V2.6 Pro | 67.3% | $0.33 | 172,106 | ||
| GLM-5.3-Flash | 66.3% | $1.43 | 292,496 | ||
| 66.2% | $0.62 | 92,248 | |||
| 66% | $2.66 | 119,319 | |||
| Claude Haiku 5.5 | 65.5% | $1.36 | 247,095 | ||
| 65.1% | $1.08 | 149,550 | |||
| Beam 1.0 | 64.7% | 63,541 | |||
| 62% | $5.35 | 83,293 | |||
| 59.8% | $3.18 | 141,615 | |||
| Mercury 3 | 57.9% | $0.19 | 114,614 | ||
| 52.8% | $1.29 | 220,731 | |||
| 41% | $1.67 | 94,711 | |||
| 40.8% | $0.25 | 62,992 |
The best score, 77.4%, costs $6.67 a task
Runs on the cost frontier score higher than any run that's cheaper. GPT-6.1 Terra comes within 4 points of the best for $0.56 a task, 12 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official Excel Modeling Benchmark v1.1 leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Fable 5.2 | 77.4% | $6.67 | 89,316 | ||
| Claude Fable 5.1 | 76.7% | $16 | 122,541 | ||
| 76.5% | $5.76 | 128,574 | |||
| 76.5% | $3.82 | 128,555 | |||
| GPT-6.2 Astra | 76% | $2.80 | 34,759 | ||
| Claude Sonnet 5.5 | 75.9% | $6.53 | 287,535 | ||
| Claude Opus 5.5 | 75.8% | $9.33 | 232,398 | ||
| 75.8% | $3.17 | 143,883 | |||
| 75% | $4.58 | 81,668 | |||
| 74.8% | $12 | 139,780 | |||
| GPT-6.2 Sol | 74.3% | $0.84 | 38,838 | ||
| GPT-6.1 Terra | 73.3% | $0.56 | 56,429 | ||
| 72.9% | $8.24 | 212,969 | |||
| GPT-6 Astra | 72.7% | $5.83 | 54,340 | ||
| 72.5% | $5.60 | 79,695 | |||
| 72.2% | $0.09 | 70,585 | |||
| 72% | $4.43 | 142,004 | |||
| Grok 4.7 | 71.5% | $6.48 | 152,252 | ||
| Kimi K3 | 71.3% | $3.07 | 95,082 | ||
| GPT-6.1 Sol | 71.1% | $1.14 | 59,382 | ||
| 70.8% | $1.00 | 79,218 | |||
| Kimi K3.1 Pro | 70% | $1.59 | 63,212 | ||
| GPT-6 Luna | 70% | $0.14 | 107,914 | ||
| 69.5% | $1.33 | 144,151 | |||
| 69.5% | $0.53 | 134,164 | |||
| 69.2% | $0.33 | 158,012 | |||
| GLM-5.3 | 69.1% | $3.79 | 179,978 | ||
| 69% | $2.47 | 170,078 | |||
| 69% | $0.79 | 102,269 | |||
| MiMo-V2.6 Flash | 68.9% | $0.11 | 157,412 | ||
| 68.7% | $0.83 | 89,247 | |||
| 67.8% | $0.27 | 139,084 | |||
| 67.8% | $0.23 | 130,189 | |||
| MiMo-V2.6 Pro | 67.3% | $0.33 | 172,106 | ||
| GLM-5.3-Flash | 66.3% | $1.43 | 292,496 | ||
| 66.2% | $0.62 | 92,248 | |||
| 66% | $2.66 | 119,319 | |||
| Claude Haiku 5.5 | 65.5% | $1.36 | 247,095 | ||
| 65.1% | $1.08 | 149,550 | |||
| Beam 1.0 | 64.7% | 63,541 | |||
| 62% | $5.35 | 83,293 | |||
| 59.8% | $3.18 | 141,615 | |||
| Mercury 3 | 57.9% | $0.19 | 114,614 | ||
| 52.8% | $1.29 | 220,731 | |||
| 41% | $1.67 | 94,711 | |||
| 40.8% | $0.25 | 62,992 |
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.
Source: Official Excel Modeling Benchmark v1.1 leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official Excel Modeling Benchmark v1.1 leaderboard and labs’ model cards
One lab 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.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Nov 5, 2026 | 69.5 | Excel Modeling Benchmark v1.1, 69.5% |
One system card reports it
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 | | 66 | Excel Modeling Benchmark v1.1 | Capabilities |
One lab claim 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. 1 of them match, which usually means one side copied the other. Every benchmark.
| Model | Lab says | Board says | Gap |
|---|---|---|---|
| | 69.5% Excel Modeling Benchmark v1.1, 69.5% | 69.5% 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 Law, finance and medicine
- MedXpertQA-MM In use Models answer expert-level medical exam questions that combine images with clinical records and test results. Scoring is accuracy.
Qwen 3.8 Max 80.4%
- HealthBench Professional In use 525 physician-authored tasks from real clinician chats (care consult, documentation, research) with physician-adjudicated rubrics. Claude Sonnet 5.5 69.2%
- HealthBench In use 5,000 realistic health conversations graded against physician-written rubrics. A length-adjusted variant penalizes verbosity. GPT-5 67.2%
- FinSearchComp In use Agents search the web to fetch live financial data, look up history, and run multi-step investigations, across 635 expert-written questions. Scored by answer accuracy.
Ling-3.1-flash 81.7%
- KorMedMCQA In use Models answer 7,469 multiple-choice questions from Korean licensing exams for doctors, nurses, pharmacists and dentists, held from 2012 to 2024. o1-preview 92.7%
- Harvey LAB-AA v1.1 In use Artificial Analysis's run of Harvey's Legal Agent Benchmark on Harvey's newer private set of 120 tasks across 24 practice areas. A deliverable with a material hallucination scores zero, and the headline is the share of judges who find every rubric criterion passed. GPT-6.2 Astra 15%
Data audit
All 12 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access The tasks are private.
- Pass Confidence Checked against a primary source.
Scores 5 pass
- Pass Independent runs Scores from the official leaderboard (47 entries), launch posts (1 score) and system cards (1 score).
- Pass Models scored 47 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 10 of the top 10 have a score, led by GPT-6.2 Astra (#1).
- Pass Headroom The best is 77.4%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on vals.ai: 46 rows for models we track and 1 other entry at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 2 pass
- Pass Lab claims The one pair agrees within 10 points.
- Pass Known issues No published audit found problems.