Tax Agent Bench leaderboard
Agentic research into US corporate tax questions. Claude Fable 5.1 leads with 49.19%.
- Models
- 73
- Leader
- Claude Fable 5.1
- Source
- Vals AI
- As of
- Oct 24, 2026
Open weightsProprietaryBest for the price
Full leaderboard
| Rank | Model | Lab | Accuracy | Cost / test | Harness | Price in / out |
|---|---|---|---|---|---|---|
| 2 | Claude Fable 5.1 | Anthropic | 49.19% | $13.18 | — | $10 / $50 |
| 3 | Claude Opus 5.5 | Anthropic | 45.57% | $15.09 | — | $4 / $20 |
| 4 | Claude Opus 5 | Anthropic | 45.55% | $5.14 | — | $5 / $25 |
| 5 | Gemini 4 Argon | 44.56% | $3.47 | — | $2 / $10 | |
| 7 | Muse Wonder Full | Meta | 43.00% | $2.15 | — | — |
| 8 | Muse Spark 1.3 Max | Meta | 42.44% | $0.39 | — | — |
| 9 | Claude Sonnet 5.5 | Anthropic | 41.96% | $9.25 | — | $2 / $10 |
| 10 | GLM-5.3 | Z.ai | 39.70% | $1.80 | — | $0.079 / $1.40 |
| 11 | Claude Fable 5 | Anthropic | 38.28% | $6.70 | — | $10 / $50 |
| 12 | Muse Wonder | Meta | 36.27% | $1.88 | — | $4 / $20 |
| 13 | Muse Spark 1.3 | Meta | 35.97% | $0.32 | — | $1.25 / $4.25 |
| 14 | Grok 4.7 | xAI | 34.20% | $1.80 | — | $2 / $6 |
| 15 | Kimi K3 | Moonshot AI | 33.37% | $2.79 | — | $0.24 / $11 |
| 16 | Grok 4.6 | xAI | 33.14% | $0.98 | — | $2 / $6 |
| 17 | Muse Spark 1.2 | Meta | 32.80% | $0.27 | — | $1.25 / $4.25 |
| 18 | Hy4 preview | Tencent | 32.62% | $0.59 | — | $0.75 / $2.25 |
| 19 | MiMo-V2.6-Pro | Xiaomi | 32.39% | $0.13 | — | $0.43 / $0.87 |
| 20 | MiniMax-M3.1-Flash | MiniMax | 32.14% | $0.32 | — | $0.15 / $0.60 |
| 21 | Gemini 3.8 Flash | 32.12% | $0.86 | — | $0.82 / $4.13 | |
| 22 | Qwen3.8-Max | Alibaba | 32.09% | $1.55 | — | $2 / $6 |
| 23 | Claude Haiku 5.5 | Anthropic | 31.92% | $1.16 | — | $0.10 / $0.50 |
| 24 | GLM-5.3-Flash | Z.ai | 31.55% | $0.14 | — | $0.15 / $0.50 |
| 25 | GPT-5.6 Sol | OpenAI | 31.09% | $7.51 | — | $4 / $20 |
| 26 | EEmber-1 | Fireworks AI | 31.08% | $2.97 | — | $3 / $15 |
| 27 | Qwen3.8-27B | Alibaba | 30.89% | $0.82 | — | $0.20 / $2.50 |
| 28 | Mistral Large 4 | Mistral AI | 30.39% | $2.72 | — | $1.36 / $4.18 |
| 29 | GPT-5.6 Terra | OpenAI | 30.04% | $4.83 | — | $2 / $12 |
| 30 | Claude Opus 4.8 | Anthropic | 30.00% | $1.69 | — | $5 / $25 |
| 31 | Claude Sonnet 5 | Anthropic | 29.37% | $1.79 | — | $2 / $10 |
| 32 | MiMo-V2.6-Flash | Xiaomi | 28.51% | $0.05 | — | $0.14 / $0.28 |
| 33 | DeepSeek-V4-Flash | DeepSeek | 28.07% | $0.16 | — | $0.042 / $0.18 |
| 34 | Step 5 Preview | StepFun | 27.27% | $0.55 | — | $1 / $2.70 |
| 36 | DeepSeek-V4.1-Flash-20260910 | DeepSeek | 26.63% | $0.13 | — | $0.15 / $0.60 |
| 37 | Muse Spark Open | Meta | 26.32% | $0.88 | — | $1.25 / $4.25 |
| 38 | Claude Sonnet 4.6 | Anthropic | 25.84% | $1.19 | — | $3 / $15 |
| 39 | DeepSeek-V4-Pro | DeepSeek | 25.17% | $0.72 | — | $0.66 / $1.98 |
| 40 | Kimi K3.1 Pro | Moonshot AI | 24.87% | $3.64 | — | $2 / $10 |
| 41 | Grok 4.5 | xAI | 24.86% | $0.47 | — | $2 / $6 |
| 42 | GPT-5.6 Luna | OpenAI | 24.82% | $0.47 | — | $0.20 / $1.20 |
| 43 | Claude Opus 4.7 | Anthropic | 23.74% | $1.27 | — | $5 / $25 |
| 44 | Gemini 3.7 Flash | 22.80% | $0.48 | — | $0.75 / $3.75 | |
| 45 | GPT-5.5 | OpenAI | 21.76% | $4.07 | — | $5 / $30 |
| 46 | GPT-6.1 Sol | OpenAI | 21.75% | $1.32 | — | $2 / $10 |
| 47 | Gemini 3.5 Flash | 21.65% | $0.86 | — | $1.50 / $9 | |
| 48 | GPT-6 Astra | OpenAI | 20.72% | $5.80 | — | $10 / $50 |
| 49 | LLing 3.0 Flash Fin | — | 20.60% | $0.03 | — | — |
| 50 | MiniMax-M3 | MiniMax | 20.59% | $0.16 | — | $0.30 / $1.20 |
| 51 | GPT-6 Luna | OpenAI | 19.95% | $0.19 | — | $0.10 / $0.50 |
| 52 | Mercury 3 | Inception | 18.17% | $0.05 | — | $0.10 / $0.35 |
| 53 | Gemini 3.6 Flash | 18.04% | $0.36 | — | $0.75 / $3.75 | |
| 54 | Qwen3.7-Max-Preview | Alibaba | 15.83% | $0.44 | — | $1.48 / $4.42 |
| 55 | IInkling-Small | Thinky | 15.39% | $0.09 | — | $0.45 / $1.20 |
| 56 | IInkling | Thinky | 15.29% | $0.35 | — | $1 / $4.05 |
| 57 | GPT-6 Sol | OpenAI | 15.00% | $2.28 | — | $2 / $10 |
| 58 | Kimi K2.6 | Moonshot AI | 12.40% | $0.57 | — | $0.65 / $3.41 |
| 59 | Gemini 3 Flash | 11.84% | $0.10 | — | $0.50 / $3 | |
| 60 | MiMo-V2.5-Pro | Xiaomi | 11.50% | $0.04 | — | $0.30 / $0.61 |
| 61 | Qwen3.7-Plus | Alibaba | 10.47% | $0.09 | — | $0.32 / $1.28 |
| 62 | Gemini 3.1 Pro Preview | 9.29% | $0.30 | — | $2 / $12 | |
| 63 | BBeam 1.0 | Reflection AI | 8.81% | N/A | — | — |
| 64 | GPT-5.4 mini | OpenAI | 8.81% | $0.81 | — | $0.75 / $4.50 |
| 65 | MiMo-V2.5 | Xiaomi | 7.77% | $0.02 | — | $0.12 / $0.24 |
| 66 | Qwen3.6-Plus | Alibaba | 7.68% | $0.30 | — | $0.33 / $1.95 |
| 67 | Gemini 3.5 Flash-Lite | 7.25% | $0.08 | — | $0.30 / $2.50 | |
| 68 | Grok 4.20 | xAI | 6.95% | $0.12 | — | $1.25 / $2.50 |
| 69 | MiniMax-M2.7 | MiniMax | 6.87% | $0.12 | — | $0.30 / $1.20 |
| 70 | Grok 4.3 | xAI | 6.18% | $0.12 | — | $1.25 / $2.50 |
| 71 | Claude Haiku 4.5 | Anthropic | 5.86% | $0.23 | — | $1 / $5 |
| 72 | GPT-5.4 nano | OpenAI | 4.97% | $0.07 | — | $0.20 / $1.25 |
| 73 | Mistral Medium 3.5 | Mistral AI | 4.48% | $1.44 | — | $1.50 / $7.50 |
| 74 | Gemini 3.1 Flash-Lite Preview | 3.11% | $0.01 | — | $0.25 / $1.50 | |
| 75 | Nemotron 3.5 Lightning | Fireworks AI | 2.59% | $0.03 | — | $0.07 / $0.20 |
| 76 | Mercury 2.5 | Inception | 2.49% | $0.02 | — | $0.04 / $0.15 |
Gemini 4 Argon
Claude Opus 5.5
Muse Wonder
MiMo-V2.6-Pro
Qwen3.8-Max
Kimi K3
GLM-5.3
GPT-5.5
ERNIE 5.1
DeepSeek-V4.1-Flash-20260910
Grok 4.20 Beta
amazon-nova-experimental-chat
Dola Seed 2.0 Pro
NVIDIA-Nemotron-3-Ultra-550B-A55B
Gemma 4 31B
Step 5 Preview


