Benchmarks · agentic
Harvey's Legal Agent Benchmark
Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools
25 models · 25 results · updated 2026-11-05 · vals.ai ↗
Leaderboard
Gemini 4 Argon high
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. 11 more models under All models in settings.
More from this benchmark
1 published measuresTime per task35 results · lower is better
8 more models under All models in settings.
All results
25 rows| # | Model | Effort | Score | Subscription $ / task | API $ / task | Time |
|---|---|---|---|---|---|---|
| 1 | Gemini 4 Argon | high | 27.1% | $7.52 | $11 | 29 min |
| 2 | Muse Spark Open | xhigh | 25.0% | $14 | $14 | 4.0 h |
| 3 | Inkling 2 Small | max | 21.7% | $1.23 | $1.23 | 22 min |
| 4 | Grok 4.7 | xhigh | 18.3% | $1.00 | $11 | 36 min |
| 5 | Gemini 4 Carbon | high | 17.5% | $2.32 | $6.52 | 29 min |
| 6 | GLM 5.3 | max | 14.6% | $0.41 | $3.99 | 32 min |
| 7 | DeepSeek V4.1 Flash 1017 | max | 14.2% | free | $0.61 | 22 min |
| 8 | MiMo V2.6 Pro | max | 13.8% | $0.18 | $0.22 | 31 min |
| 9 | MiMo V2.6 Flash | high | 13.3% | free | $0.086 | 22 min |
| 10 | Kimi K3 | max | 12.9% | $0.38 | $4.14 | 43 min |
| 11 | Hy4 | high | 12.5% | $0.30 | $1.04 | 19 min |
| 12 | Gemini 3.8 Flash | high | 12.1% | $0.15 | $3.66 | 19 min |
| 13 | DeepSeek V4 Pro 0813 | max | 10.8% | $0.80 | $0.80 | 11 min |
| 14 | Sonnet 5.5 | max | 10.4% | $0.25 | $17 | 1.2 h |
| 15 | GLM 5.3 Flash | max | 10.4% | free | $0.32 | 12 min |
| 16 | Opus 5.5 | max | 9.2% | $0.32 | $21 | 58 min |
| 17 | Hy4 preview | high | 8.8% | $0.74 | $0.98 | 33 min |
| 18 | GPT-6 Astra | max | 7.1% | $1.09 | $25 | 33 min |
| 19 | GPT-6.1 Sol | max | 6.3% | $0.21 | $3.54 | 40 min |
| 20 | Mercury 3 | high | 5.0% | $0.19 | $0.19 | 15 min |
| 21 | Haiku 5.5 | max | 4.2% | $0.090 | $4.26 | 44 min |
| 22 | GPT-6 Luna | max | 4.2% | $0.022 | $0.30 | 22 min |
| 23 | Inkling | max | 3.8% | $0.11 | $1.25 | 8.8 min |
| 24 | Inkling Small | max | 2.9% | $0.14 | $0.18 | 7.6 min |
| 25 | GPT-6.1 Terra | max | 1.7% | $0.075 | $1.48 | 14 min |