Benchmarks · agentic
Tax Agent Bench
Evaluating agents on research-grade US tax questions using the Tax Agent Bench harness
57 models · 58 results · updated 2026-10-27 · vals.ai ↗
Leaderboard
Fable 5.1 max
More from this benchmark
1 published measuresTime per task78 results · lower is better
All results
58 rows| # | Model | Effort | Tax Agent Bench | Subscription $ / task | API $ / task | Time |
|---|---|---|---|---|---|---|
| 1 | Fable 5.1 | max | 49.2% | $2.05 | $13 | 29 min |
| 2 | Gemini 4 Carbon | high | 48.9% | $6.34 | $6.34 | 35 min |
| 3 | Opus 5.5 | max | 45.6% | $0.23 | $15 | 1.1 h |
| 4 | Opus 5 | max | 45.5% | $0.089 | $5.14 | 17 min |
| 5 | Gemini 4 Argon | high | 44.6% | $1.24 | $3.47 | 16 min |
| 6 | DeepSeek V4.1 Flash 1017 | max | 44.4% | free | $0.46 | 21 min |
| 7 | Muse Spark 1.3 | max | 42.4% | $0.19 | $0.39 | 4.1 min |
| 8 | Sonnet 5.5 | max | 42.0% | $0.14 | $9.25 | 59 min |
| 9 | GLM 5.3 | max | 39.7% | $0.19 | $1.80 | 51 min |
| 10 | Fable 5 | max | 38.3% | $0.75 | $6.70 | 14 min |
| 11 | Muse Spark 1.3 | xhigh | 36.0% | $0.16 | $0.32 | 8.4 min |
| 12 | Grok 4.7 | xhigh | 34.2% | $0.17 | $1.80 | 17 min |
| 13 | Kimi K3 | max | 33.4% | $0.22 | $2.79 | 40 min |
| 14 | Grok 4.6 | high | 33.1% | $0.10 | $0.98 | 11 min |
| 15 | Muse Spark 1.2 | xhigh | 32.8% | $0.13 | $0.27 | 2.0 min |
| 16 | MiMo V2.6 Pro | high | 32.4% | $0.11 | $0.13 | 26 min |
| 17 | Gemini 3.8 Flash | high | 32.1% | $0.035 | $0.86 | 3.0 min |
| 18 | Qwen 3.8 Max | max | 32.1% | $1.55 | $1.55 | 41 min |
| 19 | Haiku 5.5 | max | 31.9% | $0.025 | $1.16 | 50 min |
| 20 | GLM 5.3 Flash | max | 31.6% | free | $0.14 | 22 min |
| 21 | GPT-5.6 Sol | max | 31.1% | $0.41 | $7.51 | 45 min |
| 22 | Qwen 3.8 27B | xhigh | 30.9% | $0.060 | $0.82 | 22 min |
| 23 | Mistral Large 4 | high | 30.4% | $2.72 | $2.72 | 57 min |
| 24 | GPT-5.6 Terra | max | 30.0% | $0.27 | $4.83 | 1.0 h |
| 25 | Opus 4.8 | max | 30.0% | $0.029 | $1.69 | 8.0 min |
| 26 | Sonnet 5 | max | 29.4% | $0.031 | $1.79 | 19 min |
| 27 | MiMo V2.6 Flash | high | 28.5% | free | $0.049 | 17 min |
| 28 | DeepSeek V4 Flash 0731 | high | 28.1% | $0.16 | $0.16 | 5.6 min |
| 29 | DeepSeek V4 Pro 0813 | max | 26.8% | $0.73 | $0.73 | 27 min |
| 30 | DeepSeek V4.1 Flash | max | 26.6% | $0.008 | $0.13 | 5.8 min |