Benchmarks · economics
CorpFin (Vals)
A private benchmark evaluating understanding of long-context credit agreements Scores are the values published by VALS AI. Source benchmark version 2.
54 models · 54 results · updated 2026-08-12 · vals.ai ↗
Leaderboard
Opus 5 max
Heavy line: best score at each price. Thin lines join one model's effort levels. Cost uses each model's median subscription plan, or API price with no plan data. 31 more models under All models in settings.
More from this benchmark
4 published measuresTime per task134 results · lower is better
34 more models under All models in settings.
Score vs any published measure3 measures: sub-scores, splits, counts
Breakdown
darker is better within each column · click a column to sort| Model | |||
|---|---|---|---|
| Opus 5 max | 68.6 | 76.0 | 74.9 |
| Fable 5 max | 66.9 | 77.0 | 71.6 |
| Kimi K3 max | 69.3 | 72.7 | 72.6 |
| Muse Spark 1.1 xhigh | 66.4 | 74.4 | 73.1 |
| Muse Spark 1.2 xhigh | 66.1 | 74.0 | 72.7 |
| Inkling Small max | 68.6 | 70.4 | 69.8 |
| Inkling max | 68.9 | 67.6 | 69.2 |
| Grok 4.3 xhigh | 66.8 | 68.8 | 70.0 |
| GPT-5.5 xhigh | 65.6 | 70.0 | 69.6 |
| MiniMax M3 max | 64.9 | 69.7 | 69.7 |
| Grok 4.5 high | 66.3 | 67.5 | 68.4 |
| Sonnet 5 max | 63.9 | 69.1 | 67.9 |
| Kimi K2.6 max | 64.8 | 67.2 | 68.2 |
| Opus 4.8 max | 64.3 | 69.8 | 66.0 |
| Grok 4.6 high | 64.5 | 66.2 | 67.8 |
| GLM 5.2 max | 63.6 | 68.4 | 66.3 |
| Opus 4.7 max | 64.3 | 67.8 | 66.1 |
| Qwen 3.8 Max | 64.6 | 65.6 | 67.4 |
| DeepSeek V4 Pro 0813 max | 63.3 | 66.2 | 66.8 |
| Sonnet 4.6 max | 63.2 | 66.1 | 66.7 |
| GPT-5.6 Terra xhigh | 63.2 | 66.3 | 66.4 |
| Muse Spark | 64.8 | 60.0 | 70.5 |
| Gemini 3.5 Flash high | 62.8 | 66.7 | 64.6 |
| GLM 5.1 max | 61.8 | 66.3 | 65.3 |
| GPT-5.6 Sol max | 61.5 | 65.2 | 66.4 |
All results
54 rows| # | Model | Effort | CorpFin (Vals) | Subscription $ / task | API $ / task | Time |
|---|---|---|---|---|---|---|
| 1 | Opus 5 | max | 73.2% | $0.015 | $0.86 | 29s |
| 2 | Fable 5 | max | 71.8% | $0.20 | $1.74 | 53s |
| 3 | Kimi K3 | max | 71.6% | $0.006 | $0.064 | 38s |
| 4 | Muse Spark 1.1 | xhigh | 71.3% | $0.11 | $0.11 | 28s |
| 5 | Muse Spark 1.2 | xhigh | 70.9% | $0.054 | $0.11 | 30s |
| 6 | Inkling Small | max | 69.6% | $0.020 | $0.025 | 45s |
| 7 | Inkling | max | 68.6% | $0.008 | $0.084 | 29s |
| 8 | Grok 4.3 | xhigh | 68.5% | $0.13 | $0.13 | 36s |
| 9 | GPT-5.5 | xhigh | 68.4% | $0.012 | $0.43 | 23s |
| 10 | MiniMax M3 | max | 68.1% | $0.008 | $0.050 | 24s |
| 11 | Grok 4.5 | high | 67.4% | $0.035 | $0.22 | 1.5 min |
| 12 | Sonnet 5 | max | 67.0% | $0.009 | $0.52 | 19s |
| 13 | Kimi K2.6 | max | 66.7% | $0.037 | $0.073 | 80s |
| 14 | Opus 4.8 | max | 66.7% | $0.015 | $0.86 | 20s |
| 15 | Grok 4.6 | high | 66.2% | $0.017 | $0.17 | 24s |
| 16 | GLM 5.2 | max | 66.1% | $0.004 | $0.12 | 25s |
| 17 | Opus 4.7 | max | 66.1% | $0.82 | $0.82 | 18s |
| 18 | Qwen 3.8 Max | max | 65.9% | $0.021 | $0.18 | 47s |
| 19 | DeepSeek V4 Pro 0813 | max | 65.4% | $0.002 | $0.002 | 33s |
| 20 | Sonnet 4.6 | max | 65.3% | $0.31 | $0.31 | 18s |
| 21 | GPT-5.6 Terra | xhigh | 65.3% | $0.005 | $0.17 | 7.7s |
| 22 | Muse Spark | 65.1% | $0.012 | $0.012 | 40s | |
| 23 | Gemini 3.5 Flash | high | 64.7% | $0.14 | $0.14 | 8.7s |
| 24 | GLM 5.1 | max | 64.5% | $0.021 | $0.079 | 68s |
| 25 | GPT-5.6 Sol | max | 64.4% | $0.013 | $0.48 | 16s |
| 26 | GPT-5.6 Luna | max | 64.2% | $0.001 | $0.019 | 17s |
| 27 | Qwen 3.7 Max | max | 63.7% | $0.067 | $0.22 | 20s |
| 28 | Qwen 3.5 Flash | max | 63.6% | $0.010 | $0.010 | 35s |
| 29 | Gemini 3.6 Flash | high | 63.3% | $0.004 | $0.14 | 6.3s |
| 30 | Qwen 3.6 27B | max | 62.3% | $0.054 | $0.054 | 63s |