BenchLeader
Menu
Best LLMsChoose a modelLeaderboardsModelsBenchmarksProvidersReleases12

Vals RSI Index

Autonomous machine-learning research work, scored against published, human and frontier-model references. Run by Vals AI.

As of 24 Oct 2026, Claude Opus 5.5 leads Vals RSI Index on BenchLeader with 37.3%, ahead of Claude Fable 5.1 at 36.1%, across 25 model configurations with a published result.

Published by
Vals AI
Category
Composite
Index weight
Reference only
Models
25
Data as of
24 Oct 2026
Newest result
15 Oct 2026

Vals AI (vals.ai).

Top 15
  1. 1Claude Opus 5.5 (max)37.3%
  2. 2Claude Fable 5.1 (max)36.1%
  3. 3Claude Opus 5 (max)33.0%
  4. 4Gemini 4 Argon (high)30.6%
  5. 5GPT-6 Sol (max)28.1%
  6. 6GPT-6 Astra (max)27.1%
  7. 7GPT-6.1 Sol (max)26.6%
  8. 8Grok 4.6 (xhigh)25.5%
  9. 9Muse Wonder Full (max)24.4%
  10. 10Claude Fable 5 (max)24.3%
  11. 11Claude Opus 4.8 (max)24.0%
  12. 12GPT-5.6 Sol (max)23.9%
  13. 13GLM 5.3 (max)22.9%
  14. 14Qwen3.8 Max (max)21.8%
  15. 15Kimi K3 (max)20.9%
25 of 25
#
1Claude Opus 5.5max37.3%72.62026-10-15
2Claude Fable 5.1max36.1%70.52026-10-15
3Claude Opus 5max33.0%68.82026-10-15
4Gemini 4 Argonhigh30.6%70.82026-10-15
5GPT-6 Solmax28.1%66.42026-10-15
6GPT-6 Astramax27.1%70.42026-10-15
7GPT-6.1 Solmax26.6%69.92026-10-15
8Grok 4.6xhigh25.5%62.52026-10-15
9Muse Wonder Fullmax24.4%70.72026-10-15
10Claude Fable 5max24.3%69.32026-10-15
11Claude Opus 4.8max24.0%63.32026-10-15
12GPT-5.6 Solmax23.9%68.02026-10-15
13GLM 5.3max22.9%63.52026-10-15
14Qwen3.8 Maxmax21.8%63.32026-10-15
15Kimi K3max20.9%64.72026-10-15
16Grok 4.7xhigh20.2%61.62026-10-15
17Gemini 3.8 Flashhigh19.9%64.42026-10-15
18Muse Spark 1.3max19.6%67.12026-10-15
19Claude Opus 4.7max19.1%62.42026-10-15
20Gemini 3.7 Flashhigh18.3%63.52026-10-15
21GPT-5.5xhigh16.5%66.12026-10-15
22GPT-5.2xhigh15.8%60.72026-10-15
23GPT-5.4xhigh15.5%64.72026-10-15
24Claude Opus 4.5high14.8%59.22026-10-15
25Kimi K2.5max6.8%–2026-10-15

More composite benchmarks · All LLM benchmarks

Cite as: BenchLeader, “Vals RSI Index leaderboard”, data as of 24 Oct 2026, https://www.benchleader.com/benchmarks/vals_rsi_index.

Vals RSI Index: questions

What does Vals RSI Index measure?
Autonomous machine-learning research work, scored against published, human and frontier-model references. Run by Vals AI. Scores are reported in percent of tasks solved; higher is better.
Which AI model leads Vals RSI Index?
Claude Opus 5.5 leads Vals RSI Index with 37.3% as of 24 Oct 2026, ahead of Claude Fable 5.1 at 36.1%.
How many models have Vals RSI Index results?
25 model configurations have a Vals RSI Index result on BenchLeader, all taken from Vals AI.
Who runs Vals RSI Index and how often is it updated?
Vals RSI Index is published by Vals AI. BenchLeader re-reads the published results once a day and records the date each result was published.
Does Vals RSI Index count toward the BenchLeader Index?
No. Vals RSI Index is shown for reference but left out of the composite index.