BenchLeader
Menu
Best LLMsChoose a modelLeaderboardsModelsBenchmarksProvidersReleases12

Excel Modeling Benchmark v1.1

Excel Modeling Benchmark v1.1, the version Vals AI now runs new models on. Run by Vals AI.

As of 24 Oct 2026, Claude Fable 5.1 leads Excel Modeling Benchmark v1.1 on BenchLeader with 76.7%, ahead of Claude Sonnet 5.5 at 75.9%, across 30 model configurations with a published result.

Published by
Vals AI
Category
Knowledge
Index weight
Reference only
Models
30
Data as of
24 Oct 2026
Newest result
20 Oct 2026

Vals AI (vals.ai).

Top 15
  1. 1Claude Fable 5.176.7%
  2. 2Claude Sonnet 5.575.9%
  3. 3Claude Opus 5.575.8%
  4. 4Muse Wonder Full (max)75.0%
  5. 5Gemini 4 Argon (high)74.8%
  6. 6Gemini 3.8 Flash (high)72.9%
  7. 7GPT-6 Astra (max)72.7%
  8. 8Muse Wonder (max)72.5%
  9. 9Qwen3.8 Max Internal72.0%
  10. 10Grok 4.7 (xhigh)71.5%
  11. 11Kimi K3 (max)71.3%
  12. 12GPT-6.1 Sol (max)71.1%
  13. 13GPT-6 Luna (max)70.0%
  14. 14Step 5 Preview69.5%
  15. 15DeepSeek V4.1 Flash 1017 (max)69.2%
30 of 30
#
1Claude Fable 5.176.7%66.42026-10-20
2Claude Sonnet 5.575.9%–2026-10-20
3Claude Opus 5.575.8%62.02026-10-20
4Muse Wonder Fullmax75.0%70.72026-10-20
5Gemini 4 Argonhigh74.8%70.82026-10-20
6Gemini 3.8 Flashhigh72.9%64.42026-10-20
7GPT-6 Astramax72.7%70.42026-10-20
8Muse Wondermax72.5%67.52026-10-20
9NewQwen3.8 Max Internal72.0%–2026-10-20
10Grok 4.7xhigh71.5%61.62026-10-20
11Kimi K3max71.3%64.72026-10-20
12GPT-6.1 Solmax71.1%69.92026-10-20
13GPT-6 Lunamax70.0%60.02026-10-20
14Step 5 Preview69.5%60.42026-10-20
15NewDeepSeek V4.1 Flash 1017max69.2%64.02026-10-20
16GLM 5.3max69.1%63.52026-10-20
17Mistral Large 4high69.0%49.82026-10-20
18MiMo-V2.6-Flash68.9%59.72026-10-20
19NewMiniMax M3.1 Flash67.8%62.02026-10-20
20DeepSeek V4.1 Flashmax67.8%61.22026-10-20
21MiMo-V2.6-Pro67.3%64.02026-10-20
22GLM 5.3 Flashmax66.3%54.22026-10-20
23Qwen3.8 Maxmax66.0%63.32026-10-20
24Claude Haiku 5.565.5%–2026-10-20
25DeepSeek V4 Promax65.1%60.82026-10-20
26NewBeam 1.064.7%51.12026-10-20
27Muse Spark Openxhigh62.0%62.02026-10-20
28MiniMax M359.8%56.42026-10-20
29NewMercury 3high57.9%–2026-10-20
30Inkling Small40.8%54.82026-10-20

More knowledge benchmarks · All LLM benchmarks

Cite as: BenchLeader, “Excel Modeling Benchmark v1.1 leaderboard”, data as of 24 Oct 2026, https://www.benchleader.com/benchmarks/vals_emb_11.

Excel Modeling Benchmark v1.1: questions

What does Excel Modeling Benchmark v1.1 measure?
Excel Modeling Benchmark v1.1, the version Vals AI now runs new models on. Run by Vals AI. Scores are reported in percent of tasks solved; higher is better.
Which AI model leads Excel Modeling Benchmark v1.1?
Claude Fable 5.1 leads Excel Modeling Benchmark v1.1 with 76.7% as of 24 Oct 2026, ahead of Claude Sonnet 5.5 at 75.9%.
How many models have Excel Modeling Benchmark v1.1 results?
30 model configurations have a Excel Modeling Benchmark v1.1 result on BenchLeader, all taken from Vals AI.
Who runs Excel Modeling Benchmark v1.1 and how often is it updated?
Excel Modeling Benchmark v1.1 is published by Vals AI. BenchLeader re-reads the published results once a day and records the date each result was published.
Does Excel Modeling Benchmark v1.1 count toward the BenchLeader Index?
No. Excel Modeling Benchmark v1.1 is shown for reference but left out of the composite index.