Quant research code generation
Generate backtest or analysis code from trading hypotheses.
Best for this use case
gpt-5-2025-08-07
Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Vals Finance Agent overall_accuracy_pct
34.2%
Best benchmark score
41.7%
Confidence
All ranked models โ top 3
Ranked Models
30
Evidence Quality
85%
Evidence Points
36
Top Signal
SWE-bench Verified Leaderboard: swe_verified_resolved_pct
All Ranked Models
| Rank | Model | Score |
|---|---|---|
| ๐ฅ | gpt-5-2025-08-07 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Vals Finance Agent overall_accuracy_pct | 34.2% |
| ๐ฅ | claude-sonnet-4 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Sonar Java Quality Leaderboard functional_skill_pct | 32.0% |
| ๐ฅ | claude-sonnet-4.6 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 29.4% |
| #4 | gpt-5.2-2025-12-11 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Vals Finance Agent overall_accuracy_pct | 29.3% |
| #5 | gemini-2.5-pro Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Vals CorpFin v2 overall_accuracy_pct | 29.1% |
| #6 | gemini-3-pro-preview Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Vals Finance Agent overall_accuracy_pct | 28.9% |
| #7 | gemini-3.1-pro-preview Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 28.4% |
| #8 | gpt-5-mini-2025-08-07 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Vals Finance Agent overall_accuracy_pct | 27.4% |
| #9 | Grok-4-0709 Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 27.1% |
| #10 | gpt-4.1-20250414 Strong on Vals Tax Eval v2 overall_accuracy_pct and SWE-bench Verified Leaderboard swe_verified_resolved_pct | 25.9% |
| #11 | Kimi K2 Thinking Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Sonar Java Quality Leaderboard functional_skill_pct | 24.1% |
| #12 | gpt-5.4-2026-03-05 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 23.5% |
| #13 | gemini-3-flash-preview Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Tax Eval v2 overall_accuracy_pct | 22.1% |
| #14 | o3-20250416 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Vals Tax Eval v2 overall_accuracy_pct | 21.7% |
| #15 | kimi-k2.5-thinking Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 21.6% |
| #16 | claude-opus-4-5-20251101 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Vals Tax Eval v2 overall_accuracy_pct | 21.5% |
| #17 | gpt-5.1-2025-11-13 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 21.4% |
| #18 | gemini-3.1-flash-lite-preview Strong on Vals Finance Agent overall_accuracy_pct and Vals Tax Eval v2 overall_accuracy_pct | 21.2% |
| #19 | claude-opus-4-6-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 21.0% |
| #20 | grok-4-fast-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Tax Eval v2 overall_accuracy_pct | 20.8% |
| #21 | grok-4-1-fast-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 20.4% |
| #22 | claude-opus-4-5-20251101-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 20.3% |
| #23 | glm-4.7 Strong on Sonar Java Quality Leaderboard functional_skill_pct and Vals Finance Agent overall_accuracy_pct | 19.7% |
| #24 | minimax-m2.1 Strong on Sonar Java Quality Leaderboard functional_skill_pct and Vals CorpFin v2 overall_accuracy_pct | 18.9% |
| #25 | claude-sonnet-4-5-20250929-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 18.8% |
| #26 | grok-4.20-0309-reasoning Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 18.1% |
| #28 | claude-opus-4-6 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and OpenHands Issue Resolution issue_resolution_score_pct | 17.7% |
| #29 | o4-mini Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Vals Tax Eval v2 overall_accuracy_pct | 17.4% |
| #30 | qwen3.5-flash Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Tax Eval v2 overall_accuracy_pct | 17.1% |
| #33 | gpt-4.1-mini-20250414 Strong on Vals Tax Eval v2 overall_accuracy_pct and Galileo Agent Leaderboard v2 Banking AC | 16.6% |
Compare Models
โถRanking diagnostics & missing models
Source lift
Ranked
59
Sources
8
Quality
Good
Vals Tax Eval v2
Vals CorpFin v2
Vals GPQA
Vals Mortgage Tax
Missing frontier models
No obvious gaps right now.
โถTaxonomy & task details
Core tasks
Required modes
Domains
Related in Finance
Thesis red teaming
Stress-test an investment thesis with counterarguments and risk.
Earnings call synthesis
Summarize earnings calls into key points, tone, and risks.
Transaction anomaly narrative
Summarize anomalies into hypotheses, evidence, and follow-up actions.
Accounts payable invoice extraction (text)
Extract structured fields from invoices/receipts for AP workflows.