Benchmark Almanac

Excel Modeling Benchmark v1.1

Claude Fable 5.2 77.4% leads since November 2026
Claude Fable 5.2 77.4% leads since November 2026
In use
Version 1.1

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
Language
English
In and out
Text, Tables → Actions, Tables
Interaction
Agentic
Environment
Microsoft Excel
Items from
Another benchmark
Run by
A host
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
47
Entries on its own leaderboard, 46 models we track
1
Launch post lists it, from 1 lab
1
System card reports it, from 1 lab

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.

  1. 1 Claude Fable 5.2 77.4%
  2. 2 Claude Fable 5.1 76.7%
  3. 3 Gemini 4 Carbon 76.5%
  4. 4 Gemini 4 Neon 76.5%
  5. 5 GPT-6.2 Astra 76%
  6. 6 Claude Sonnet 5.5 75.9%
  7. 7 Claude Opus 5.5 75.8%
  8. 8 Gemini 4 Hydrogen 75.8%
  9. 9 Muse Wonder Full 75%
  10. 10 Gemini 4 Argon 74.8%
  11. 11 GPT-6.2 Sol 74.3%
  12. 12 GPT-6.1 Terra 73.3%
  13. 13 Gemini 3.8 Flash 72.9%
  14. 14 GPT-6 Astra 72.7%
  15. 15 Muse Wonder 72.5%
  16. 16 Muse Ember 72.2%
  17. 17 Qwen3.8 Max (0902) 72%
  18. 18 Grok 4.7 71.5%
  19. 19 Kimi K3 71.3%
  20. 20 GPT-6.1 Sol 71.1%
  21. 21 Qwen4-Max 70.8%
  22. 22 Kimi K3.1 Pro 70%
  23. 23 GPT-6 Luna 70%
  24. 24 Step 5 Preview 69.5%
  25. 25 Inkling 2 Small 69.5%
  26. 26 DeepSeek V4.1 Flash 1017 69.2%
  27. 27 GLM-5.3 69.1%
  28. 28 Mistral Large 4 Preview 69%
  29. 29 Tencent Hy4 preview 69%
  30. 30 MiMo-V2.6 Flash 68.9%
  31. 31 Mistral Large 4 68.7%
  32. 32 MiniMax-M3.1-Flash 67.8%
  33. 33 DeepSeek V4.1 Flash 67.8%
  34. 34 MiMo-V2.6 Pro 67.3%
  35. 35 GLM-5.3-Flash 66.3%
  36. 36 Tencent Hy4 66.2%
  37. 37 Qwen 3.8 Max 66%
  38. 38 Claude Haiku 5.5 65.5%
  39. 39 DeepSeek V4 Pro 0813 65.1%
  40. 40 Beam 1.0 64.7%
  41. 41 Hy4 Flash 63%
  42. 42 Muse Spark Open 62%
  43. 43 MiniMax-M3 59.8%
  44. 44 Mercury 3 57.9%
  45. 45 Nemotron 3.5 Super VL 52.8%
  46. 46 Inkling 41%
  47. 47 Inkling-Small 40.8%

Source: Official Excel Modeling Benchmark v1.1 leaderboard

Source: Official Excel Modeling Benchmark v1.1 leaderboard

Sources: Official Excel Modeling Benchmark v1.1 leaderboard and labs’ model cards

#EntryScore ± 95% CISettingDateSource
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 Gemini 4 Carbon 76.5% ±4.3 Oct 2026 Official leaderboard
4 Gemini 4 Neon 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 Gemini 4 Hydrogen 75.8% ±4 Nov 2026 Official leaderboard
9 Muse Wonder Full 75% ±4.2 Oct 2026 Official leaderboard
10 Gemini 4 Argon 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 Gemini 3.8 Flash 72.9% ±4.8 Sep 2026 Official leaderboard
14 GPT-6 Astra 72.7% ±4.5 Sep 2026 Official leaderboard
15 Muse Wonder 72.5% ±4.7 Oct 2026 Official leaderboard
16 Muse Ember 72.2% ±4.5 Nov 2026 Official leaderboard
17 Qwen3.8 Max (0902) 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 Qwen4-Max 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 Step 5 Preview 69.5% ±4.9 Sep 2026 Official leaderboard
25 Inkling 2 Small 69.5% ±4.9 Nov 2026 Official leaderboard
26 DeepSeek V4.1 Flash 1017 69.2% ±4.7 Oct 2026 Official leaderboard
27 GLM-5.3 69.1% ±5.2 Aug 2026 Official leaderboard
28 Mistral Large 4 Preview 69% ±4.6 Oct 2026 Official leaderboard
29 Tencent Hy4 preview 69% ±4.7 Aug 2026 Official leaderboard
30 MiMo-V2.6 Flash 68.9% ±4.4 Sep 2026 Official leaderboard
31 Mistral Large 4 68.7% ±4.8 Oct 2026 Official leaderboard
32 MiniMax-M3.1-Flash 67.8% ±4.5 Oct 2026 Official leaderboard
33 DeepSeek V4.1 Flash 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 Tencent Hy4 66.2% ±5.2 Nov 2026 Official leaderboard
37 Qwen 3.8 Max 66% ±5.3 Aug 2026 Official leaderboard
38 Claude Haiku 5.5 65.5% ±7.2 Oct 2026 Official leaderboard
39 DeepSeek V4 Pro 0813 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 Muse Spark Open 62% ±5.3 Oct 2026 Official leaderboard
43 MiniMax-M3 59.8% ±5 Jun 2026 Official leaderboard
44 Mercury 3 57.9% ±5.7 Oct 2026 Official leaderboard
45 Nemotron 3.5 Super VL 52.8% ±5.5 Oct 2026 Official leaderboard
46 Inkling 41% ±5.8 Jul 2026 Official leaderboard
47 Inkling-Small 40.8% ±6.3 Jul 2026 Official leaderboard
#ModelScore ± 95% CISettingDateSource
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 Gemini 4 Carbon 76.5% ±4.3 Oct 2026 Official leaderboard
4 Gemini 4 Neon 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 Gemini 4 Hydrogen 75.8% ±4 Nov 2026 Official leaderboard
9 Muse Wonder Full 75% ±4.2 Oct 2026 Official leaderboard
10 Gemini 4 Argon 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 Gemini 3.8 Flash 72.9% ±4.8 Sep 2026 Official leaderboard
14 GPT-6 Astra 72.7% ±4.5 Sep 2026 Official leaderboard
15 Muse Wonder 72.5% ±4.7 Oct 2026 Official leaderboard
16 Muse Ember 72.2% ±4.5 Nov 2026 Official leaderboard
17 Qwen3.8 Max (0902) 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 Qwen4-Max 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 Step 5 Preview 69.5% ±4.9 Sep 2026 Official leaderboard
25 Inkling 2 Small 69.5% ±4.9 Nov 2026 Official leaderboard
26 DeepSeek V4.1 Flash 1017 69.2% ±4.7 Oct 2026 Official leaderboard
27 GLM-5.3 69.1% ±5.2 Aug 2026 Official leaderboard
28 Mistral Large 4 Preview 69% ±4.6 Oct 2026 Official leaderboard
29 Tencent Hy4 preview 69% ±4.7 Aug 2026 Official leaderboard
30 MiMo-V2.6 Flash 68.9% ±4.4 Sep 2026 Official leaderboard
31 Mistral Large 4 68.7% ±4.8 Oct 2026 Official leaderboard
32 MiniMax-M3.1-Flash 67.8% ±4.5 Oct 2026 Official leaderboard
33 DeepSeek V4.1 Flash 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 Tencent Hy4 66.2% ±5.2 Nov 2026 Official leaderboard
37 Qwen 3.8 Max 66% ±5.3 Aug 2026 Official leaderboard
38 Claude Haiku 5.5 65.5% ±7.2 Oct 2026 Official leaderboard
39 DeepSeek V4 Pro 0813 65.1% ±4.6 Aug 2026 Official leaderboard
40 Beam 1.0 64.7% ±4.4 Oct 2026 Official leaderboard
41 Muse Spark Open 62% ±5.3 Oct 2026 Official leaderboard
42 MiniMax-M3 59.8% ±5 Jun 2026 Official leaderboard
43 Mercury 3 57.9% ±5.7 Oct 2026 Official leaderboard
44 Nemotron 3.5 Super VL 52.8% ±5.5 Oct 2026 Official leaderboard
45 Inkling 41% ±5.8 Jul 2026 Official leaderboard
46 Inkling-Small 40.8% ±6.3 Jul 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Fable 5.2 77.4% Nov 2026 Official leaderboard
2 Claude Fable 5.1 76.7% Sep 2026 Official leaderboard
3 Gemini 4 Carbon 76.5% Oct 2026 Official leaderboard
4 Gemini 4 Neon 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 Gemini 4 Hydrogen 75.8% Nov 2026 Official leaderboard
9 Muse Wonder Full 75% Oct 2026 Official leaderboard
10 Gemini 4 Argon 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 Gemini 3.8 Flash 72.9% Sep 2026 Official leaderboard
14 GPT-6 Astra 72.7% Sep 2026 Official leaderboard
15 Muse Wonder 72.5% Oct 2026 Official leaderboard
16 Muse Ember 72.2% Nov 2026 Official leaderboard
17 Qwen3.8 Max (0902) 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 Qwen4-Max 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 Step 5 Preview 69.5% Sep 2026 Official leaderboard
25 Inkling 2 Small 69.5% Nov 2026 Official leaderboard
26 DeepSeek V4.1 Flash 1017 69.2% Oct 2026 Official leaderboard
27 GLM-5.3 69.1% Aug 2026 Official leaderboard
28 Mistral Large 4 Preview 69% Oct 2026 Official leaderboard
29 Tencent Hy4 preview 69% Aug 2026 Official leaderboard
30 MiMo-V2.6 Flash 68.9% Sep 2026 Official leaderboard
31 Mistral Large 4 68.7% Oct 2026 Official leaderboard
32 MiniMax-M3.1-Flash 67.8% Oct 2026 Official leaderboard
33 DeepSeek V4.1 Flash 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 Tencent Hy4 66.2% Nov 2026 Official leaderboard
37 Inkling 2 Mini 66% Nov 2026 Lab model card
38 Qwen 3.8 Max 66% Aug 2026 Official leaderboard
39 Claude Haiku 5.5 65.5% Oct 2026 Official leaderboard
40 DeepSeek V4 Pro 0813 65.1% Aug 2026 Official leaderboard
41 Beam 1.0 64.7% Oct 2026 Official leaderboard
42 Muse Spark Open 62% Oct 2026 Official leaderboard
43 MiniMax-M3 59.8% Jun 2026 Official leaderboard
44 Mercury 3 57.9% Oct 2026 Official leaderboard
45 Nemotron 3.5 Super VL 52.8% Oct 2026 Official leaderboard
46 Inkling 41% Jul 2026 Official leaderboard
47 Inkling-Small 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.

40% 60% 80% 100% 1001,00010K Latency (mean per test) (s), log scale, lower is better Accuracy Claude Fable 5.2Gemini 4 NeonGemini 4 HydrogenMuse Ember 40% 60% 80% 100% 1001,00010K Latency (mean per test) (s), log scale, lower is better Accuracy Claude Fable 5.2Gemini 4 NeonGemini 4 HydrogenMuse Ember
ModelSettingAccuracyLatency (mean per test)
Claude Fable 5.2 77.4% 979.09 s
Claude Fable 5.1 76.7% 1,772 s
Gemini 4 Carbon 76.5% 1,649 s
Gemini 4 Neon 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
Gemini 4 Hydrogen 75.8% 662.89 s
Muse Wonder Full 75% 1,685 s
Gemini 4 Argon 74.8% 2,306 s
GPT-6.2 Sol 74.3% 887.08 s
GPT-6.1 Terra 73.3% 756.89 s
Gemini 3.8 Flash 72.9% 769.2 s
GPT-6 Astra 72.7% 804.28 s
Muse Wonder 72.5% 1,034 s
Muse Ember 72.2% 289.84 s
Qwen3.8 Max (0902) 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
Qwen4-Max 70.8% 970.57 s
Kimi K3.1 Pro 70% 1,283 s
GPT-6 Luna 70% 1,041 s
Step 5 Preview 69.6% 2,615 s
Inkling 2 Small 69.5% 833.92 s
DeepSeek V4.1 Flash 1017 69.2% 1,972 s
GLM-5.3 69.1% 2,172 s
Mistral Large 4 Preview 69% 4,905 s
Tencent Hy4 preview 69% 1,839 s
MiMo-V2.6 Flash 68.9% 1,522 s
Mistral Large 4 68.7% 1,387 s
MiniMax-M3.1-Flash 67.8% 1,848 s
DeepSeek V4.1 Flash 67.8% 780.46 s
MiMo-V2.6 Pro 67.4% 3,314 s
GLM-5.3-Flash 66.3% 4,495 s
Tencent Hy4 66.2% 1,059 s
Qwen 3.8 Max 66% 3,467 s
Claude Haiku 5.5 65.5% 1,196 s
DeepSeek V4 Pro 0813 65.1% 2,247 s
Beam 1.0 64.7% 1,204 s
Hy4 Flash 63% 427.58 s
Muse Spark Open 62% 5,079 s
MiniMax-M3 59.8% 1,299 s
Mercury 3 57.9% 531.28 s
Nemotron 3.5 Super VL 52.8% 816.73 s
Inkling 41% 1,582 s
Inkling-Small 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.

40% 60% 80% 100% 1001,00010K Latency (mean per test) (s), log scale, lower is better Accuracy Claude Fable 5.2Gemini 4 NeonGemini 4 HydrogenMuse Ember 40% 60% 80% 100% 1001,00010K Latency (mean per test) (s), log scale, lower is better Accuracy Claude Fable 5.2Gemini 4 NeonGemini 4 HydrogenMuse Ember
ModelSettingAccuracyLatency (mean per test)
Claude Fable 5.2 77.4% 979.09 s
Claude Fable 5.1 76.7% 1,772 s
Gemini 4 Carbon 76.5% 1,649 s
Gemini 4 Neon 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
Gemini 4 Hydrogen 75.8% 662.89 s
Muse Wonder Full 75% 1,685 s
Gemini 4 Argon 74.8% 2,306 s
GPT-6.2 Sol 74.3% 887.08 s
GPT-6.1 Terra 73.3% 756.89 s
Gemini 3.8 Flash 72.9% 769.2 s
GPT-6 Astra 72.7% 804.28 s
Muse Wonder 72.5% 1,034 s
Muse Ember 72.2% 289.84 s
Qwen3.8 Max (0902) 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
Qwen4-Max 70.8% 970.57 s
Kimi K3.1 Pro 70% 1,283 s
GPT-6 Luna 70% 1,041 s
Step 5 Preview 69.6% 2,615 s
Inkling 2 Small 69.5% 833.92 s
DeepSeek V4.1 Flash 1017 69.2% 1,972 s
GLM-5.3 69.1% 2,172 s
Mistral Large 4 Preview 69% 4,905 s
Tencent Hy4 preview 69% 1,839 s
MiMo-V2.6 Flash 68.9% 1,522 s
Mistral Large 4 68.7% 1,387 s
MiniMax-M3.1-Flash 67.8% 1,848 s
DeepSeek V4.1 Flash 67.8% 780.46 s
MiMo-V2.6 Pro 67.4% 3,314 s
GLM-5.3-Flash 66.3% 4,495 s
Tencent Hy4 66.2% 1,059 s
Qwen 3.8 Max 66% 3,467 s
Claude Haiku 5.5 65.5% 1,196 s
DeepSeek V4 Pro 0813 65.1% 2,247 s
Beam 1.0 64.7% 1,204 s
Muse Spark Open 62% 5,079 s
MiniMax-M3 59.8% 1,299 s
Mercury 3 57.9% 531.28 s
Nemotron 3.5 Super VL 52.8% 816.73 s
Inkling 41% 1,582 s
Inkling-Small 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.

OpenAI Google DeepMind Anthropic Meta Cost frontier One model at each effort level
0% 20% 40% 60% 80% 100% $0.01 $0.10 $1.00 $10 $100 Cost per task, log scale Claude Fable 5.2 GPT-6.2 Sol Muse Ember 0% 20% 40% 60% 80% 100% $0.01 $0.10 $1.00 $10 $100 Cost per task, log scale Claude Fable 5.2 Muse Ember

Source: Official Excel Modeling Benchmark v1.1 leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Claude Fable 5.2 77.4% $6.67 89,316
Claude Fable 5.1 76.7% $16 122,541
Gemini 4 Carbon 76.5% $5.76 128,574
Gemini 4 Neon 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
Gemini 4 Hydrogen 75.8% $3.17 143,883
Muse Wonder Full 75% $4.58 81,668
Gemini 4 Argon 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
Gemini 3.8 Flash 72.9% $8.24 212,969
GPT-6 Astra 72.7% $5.83 54,340
Muse Wonder 72.5% $5.60 79,695
Muse Ember 72.2% $0.09 70,585
Qwen3.8 Max (0902) 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
Qwen4-Max 70.8% $1.00 79,218
Kimi K3.1 Pro 70% $1.59 63,212
GPT-6 Luna 70% $0.14 107,914
Step 5 Preview 69.5% $1.33 144,151
Inkling 2 Small 69.5% $0.53 134,164
DeepSeek V4.1 Flash 1017 69.2% $0.33 158,012
GLM-5.3 69.1% $3.79 179,978
Mistral Large 4 Preview 69% $2.47 170,078
Tencent Hy4 preview 69% $0.79 102,269
MiMo-V2.6 Flash 68.9% $0.11 157,412
Mistral Large 4 68.7% $0.83 89,247
MiniMax-M3.1-Flash 67.8% $0.27 139,084
DeepSeek V4.1 Flash 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
Tencent Hy4 66.2% $0.62 92,248
Qwen 3.8 Max 66% $2.66 119,319
Claude Haiku 5.5 65.5% $1.36 247,095
DeepSeek V4 Pro 0813 65.1% $1.08 149,550
Beam 1.0 64.7% 63,541
Muse Spark Open 62% $5.35 83,293
MiniMax-M3 59.8% $3.18 141,615
Mercury 3 57.9% $0.19 114,614
Nemotron 3.5 Super VL 52.8% $1.29 220,731
Inkling 41% $1.67 94,711
Inkling-Small 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.

OpenAI Google DeepMind Anthropic Meta Cost frontier One model at each effort level
0% 20% 40% 60% 80% 100% $0.01 $0.10 $1.00 $10 $100 Cost per task, log scale Claude Fable 5.2 GPT-6.2 Sol Muse Ember 0% 20% 40% 60% 80% 100% $0.01 $0.10 $1.00 $10 $100 Cost per task, log scale Claude Fable 5.2 Muse Ember

Source: Official Excel Modeling Benchmark v1.1 leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Claude Fable 5.2 77.4% $6.67 89,316
Claude Fable 5.1 76.7% $16 122,541
Gemini 4 Carbon 76.5% $5.76 128,574
Gemini 4 Neon 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
Gemini 4 Hydrogen 75.8% $3.17 143,883
Muse Wonder Full 75% $4.58 81,668
Gemini 4 Argon 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
Gemini 3.8 Flash 72.9% $8.24 212,969
GPT-6 Astra 72.7% $5.83 54,340
Muse Wonder 72.5% $5.60 79,695
Muse Ember 72.2% $0.09 70,585
Qwen3.8 Max (0902) 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
Qwen4-Max 70.8% $1.00 79,218
Kimi K3.1 Pro 70% $1.59 63,212
GPT-6 Luna 70% $0.14 107,914
Step 5 Preview 69.5% $1.33 144,151
Inkling 2 Small 69.5% $0.53 134,164
DeepSeek V4.1 Flash 1017 69.2% $0.33 158,012
GLM-5.3 69.1% $3.79 179,978
Mistral Large 4 Preview 69% $2.47 170,078
Tencent Hy4 preview 69% $0.79 102,269
MiMo-V2.6 Flash 68.9% $0.11 157,412
Mistral Large 4 68.7% $0.83 89,247
MiniMax-M3.1-Flash 67.8% $0.27 139,084
DeepSeek V4.1 Flash 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
Tencent Hy4 66.2% $0.62 92,248
Qwen 3.8 Max 66% $2.66 119,319
Claude Haiku 5.5 65.5% $1.36 247,095
DeepSeek V4 Pro 0813 65.1% $1.08 149,550
Beam 1.0 64.7% 63,541
Muse Spark Open 62% $5.35 83,293
MiniMax-M3 59.8% $3.18 141,615
Mercury 3 57.9% $0.19 114,614
Nemotron 3.5 Super VL 52.8% $1.29 220,731
Inkling 41% $1.67 94,711
Inkling-Small 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.

Anthropic
Own leaderboard 2 leaders

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.

Plot with other benchmarks
On the benchmark’s own leaderboard Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) Claude Fable 5.2 Claude Fable 5.1 Kimi K3 MiniMax-M3 0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) Claude Fable 5.2 MiniMax-M3

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.

Thinking Machines
DateLaunch postScoreAs the post writes it
Nov 5, 2026 Inkling 2 Small 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.

DateDocumentScoreAs the document writes itSection
Nov 20, 2026 Inkling 2 Mini model card 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
Inkling 2 Small 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.

Anthropic
Excel Modeling Benchmark v1.1 4 leaders

Source: Official leaderboards

More in Law, finance and medicine

All 637 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.

How we check