Benchmarks · composite
Vals RSI Index v1.1: Post-training: Finance Agent
Can a model do the research that builds the next model? Autonomous LLM R&D scored against frozen published, human, and frontier-model references. Published Post-training: Finance Agent score in percentage points.
21 models · 21 results · updated 2026-10-15 · vals.ai ↗
Leaderboard
Opus 5.5 max
More from this benchmark
6 published measuresScore vs any published measure6 measures: sub-scores, splits, counts
Breakdown
darker is better within each column · click a column to sort| Model | |||||
|---|---|---|---|---|---|
| GPT-6 Sol max | 3205.7M | 3.1M | 991k | 3189.8M | 15.8M |
| Gemini 4 Argon max | 250.0M | 2.3M | 627k | 188.7M | 0 |
| GPT-6.1 Sol max | 285.1M | 3.0M | 2.2M | 270.6M | 14.1M |
| Grok 4.7 max | 230.8M | 692k | 271k | 195.7M | 0 |
All results
21 rows| # | Model | Effort | Score |
|---|---|---|---|
| 1 | Opus 5.5 | max | 35.1% |
| 2 | Opus 5 | max | 31.8% |
| 3 | Fable 5.1 | max | 28.0% |
| 4 | GPT-6 Sol | max | 16.3% |
| 5 | Gemini 4 Argon | max | 15.4% |
| 6 | GPT-6 Astra | max | 7.8% |
| 7 | Fable 5 | max | 0.0% |
| 8 | Opus 4.7 | max | 0.0% |
| 9 | Opus 4.8 | max | 0.0% |
| 10 | Gemini 3.7 Flash | max | 0.0% |
| 11 | Gemini 3.8 Flash | max | 0.0% |
| 12 | GLM 5.3 | max | 0.0% |
| 13 | GPT-5.4 | xhigh | 0.0% |
| 14 | GPT-5.5 | xhigh | 0.0% |
| 15 | GPT-5.6 Sol | max | 0.0% |
| 16 | GPT-6.1 Sol | max | 0.0% |
| 17 | Grok 4.6 | max | 0.0% |
| 18 | Grok 4.7 | max | 0.0% |
| 19 | Kimi K3 | max | 0.0% |
| 20 | Muse Spark 1.3 | max | 0.0% |
| 21 | Qwen 3.8 Max | max | 0.0% |