Finance Agent leaderboard
The core tasks of a financial analyst, done as an agent with research tools. Claude Opus 5.5 leads with 67.85%.
- Models
- 30
- Leader
- Claude Opus 5.5
- 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 |
|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | Anthropic | 67.85% | $8.91 | — | $4 / $20 |
| 2 | Gemini 4 Argon | 67.66% | $4.32 | — | $2 / $10 | |
| 3 | Muse Wonder Full | Meta | 67.58% | $2.68 | — | — |
| 4 | Claude Sonnet 5.5 | Anthropic | 67.28% | $6.95 | — | $2 / $10 |
| 5 | Gemini 3.8 Flash | 65.76% | $1.99 | — | $0.82 / $4.13 | |
| 6 | Muse Wonder | Meta | 65.55% | $2.62 | — | $4 / $20 |
| 8 | Claude Haiku 5.5 | Anthropic | 65.37% | $1.64 | — | $0.10 / $0.50 |
| 9 | GLM-5.3 | Z.ai | 65.00% | $1.03 | — | $0.079 / $1.40 |
| 10 | MiMo-V2.6-Pro | Xiaomi | 64.26% | $0.18 | — | $0.43 / $0.87 |
| 11 | MiMo-V2.6-Flash | Xiaomi | 63.32% | $0.07 | — | $0.14 / $0.28 |
| 12 | DeepSeek-V4.1-Flash-20260910 | DeepSeek | 62.93% | $0.47 | — | $0.15 / $0.60 |
| 13 | GPT-6.1 Sol | OpenAI | 61.82% | $1.63 | — | $2 / $10 |
| 14 | Hy4 preview | Tencent | 61.62% | $0.67 | — | $0.75 / $2.25 |
| 15 | Kimi K3.1 Pro | Moonshot AI | 61.49% | $2.29 | — | $2 / $10 |
| 16 | Mistral Large 4 | Mistral AI | 61.38% | $1.02 | — | $1.36 / $4.18 |
| 17 | Muse Spark Open | Meta | 60.66% | $2.76 | — | $1.25 / $4.25 |
| 18 | GLM-5.3-Flash | Z.ai | 60.59% | $0.07 | — | $0.15 / $0.50 |
| 19 | Grok 4.7 | xAI | 60.59% | $2.24 | — | $2 / $6 |
| 20 | GPT-6 Astra | OpenAI | 60.43% | $7.82 | — | $10 / $50 |
| 21 | Kimi K3 | Moonshot AI | 60.01% | $1.88 | — | $0.24 / $11 |
| 22 | Step 5 Preview | StepFun | 58.90% | $0.58 | — | $1 / $2.70 |
| 23 | Qwen3.8-Max | Alibaba | 58.83% | $2.99 | — | $2 / $6 |
| 24 | MiniMax-M3.1-Flash | MiniMax | 58.83% | $0.16 | — | $0.15 / $0.60 |
| 25 | DeepSeek-V4-Pro | DeepSeek | 57.12% | $0.82 | — | $0.66 / $1.98 |
| 26 | GPT-6 Luna | OpenAI | 56.84% | $0.12 | — | $0.10 / $0.50 |
| 27 | Mercury 3 | Inception | 54.71% | $0.06 | — | $0.10 / $0.35 |
| 28 | MiniMax-M3 | MiniMax | 54.34% | $0.30 | — | $0.30 / $1.20 |
| 29 | BBeam 1.0 | Reflection AI | 51.83% | N/A | — | — |
| 30 | IInkling | Thinky | 49.87% | $0.89 | — | $1 / $4.05 |
| 31 | IInkling-Small | Thinky | 44.78% | $0.21 | — | $0.45 / $1.20 |
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


