Professional · best for
Top picks for Financial Analysis (2026)
Reading earnings, modeling cash flows. Ranked from 352 live models on the OpenRouter catalog, weighted for reasoning quality, tool calling, structured output.
What this is
A capability-matched shortlist, not a benchmark-tested winner. Models are scored by the fit of their declared specs (structured output, reasoning, context, modality, price) against Financial Analysis. Pair with benchmark sources like Artificial Analysis or LMSys Arena before you ship. Full methodology →
| # | Model | Score | In / 1M | Out / 1M | Context | |
|---|---|---|---|---|---|---|
| 1 | Xiaomi: MiMo-V2.5xiaomi/mimo-v2.5 | 120 | $0.40 | $2.00 | 1,048,576 | Details → |
| 2 | MoonshotAI: Kimi K2.6moonshotai/kimi-k2.6 | 120 | $0.74 | $4.66 | 256,000 | Details → |
| 3 | Google: Gemma 4 26B A4B (free)google/gemma-4-26b-a4b-it:free | 120 | Free | Free | 262,144 | Details → |
| 4 | Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it | 120 | $0.06 | $0.33 | 262,144 | Details → |
| 5 | Google: Gemma 4 31B (free)google/gemma-4-31b-it:free | 120 | Free | Free | 262,144 | Details → |
| 6 | Google: Gemma 4 31Bgoogle/gemma-4-31b-it | 120 | $0.13 | $0.38 | 262,144 | Details → |
| 7 | Qwen: Qwen3.6 Plusqwen/qwen3.6-plus | 120 | $0.33 | $1.95 | 1,000,000 | Details → |
| 8 | Z.ai: GLM 5V Turboz-ai/glm-5v-turbo | 120 | $1.20 | $4.00 | 202,752 | Details → |
| 9 | xAI: Grok 4.20x-ai/grok-4.20 | 120 | $2.00 | $6.00 | 2,000,000 | Details → |
| 10 | Xiaomi: MiMo-V2-Omnixiaomi/mimo-v2-omni | 120 | $0.40 | $2.00 | 262,144 | Details → |
| 11 | OpenAI: GPT-5.4 Nanoopenai/gpt-5.4-nano | 120 | $0.20 | $1.25 | 400,000 | Details → |
| 12 | OpenAI: GPT-5.4 Miniopenai/gpt-5.4-mini | 120 | $0.75 | $4.50 | 400,000 | Details → |
| 13 | Mistral: Mistral Small 4mistralai/mistral-small-2603 | 120 | $0.15 | $0.60 | 262,144 | Details → |
| 14 | ByteDance Seed: Seed-2.0-Litebytedance-seed/seed-2.0-lite | 120 | $0.25 | $2.00 | 262,144 | Details → |
| 15 | Qwen: Qwen3.5-9Bqwen/qwen3.5-9b | 120 | $0.10 | $0.15 | 262,144 | Details → |
How we ranked these
For Financial Analysis, we weight models on reasoning quality, tool calling, structured output. Higher means better. Scores combine each model's public metadata (context length, modality support, tool calling, structured output, reasoning capability) with live pricing. See full methodology →
Related tasks
Professional
Best for Legal Drafting
Contracts, memos, briefs that need careful precision.
Professional
Best for Legal Research
Case law and statute analysis.
Professional
Best for Contract Review
Identifying risk terms in business contracts.
Professional
Best for Medical Note Summarization
Patient note distillation. Not a substitute for a doctor.
Professional
Best for Scientific Research
Reading papers, designing experiments, interpreting results.