Component selection assistant
Recommend components under constraints with evidence and tradeoffs.
Best for this use case
gemini-3.1-pro-preview
Strong on Vals SWE-bench overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct
35.5%
Best benchmark score
39.5%
Confidence
All ranked models — top 3
Ranked Models
30
Evidence Quality
85%
Evidence Points
22
Top Signal
Vals SWE-bench: overall_accuracy_pct
All Ranked Models
| Rank | Model | Score |
|---|---|---|
| 🥇 | gemini-3.1-pro-preview Strong on Vals SWE-bench overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 35.5% |
| 🥈 | gpt-5-2025-08-07 Strong on Aider Polyglot Leaderboard percent_correct_pct and SWE-bench Verified Leaderboard swe_verified_resolved_pct | 34.9% |
| 🥉 | gemini-2.5-pro Strong on FACTS Benchmark Suite facts_grounding_score_pct and SWE-bench Verified Leaderboard swe_verified_resolved_pct | 30.4% |
| #4 | gemini-3-pro-preview Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Vals SWE-bench overall_accuracy_pct | 29.6% |
| #5 | gpt-5-mini-2025-08-07 Strong on Vals LiveCodeBench overall_accuracy_pct and SWE-bench Verified Leaderboard swe_verified_resolved_pct | 29.6% |
| #6 | gpt-5.2-2025-12-11 Strong on FACTS Benchmark Suite facts_grounding_score_pct and SWE-bench Verified Leaderboard swe_verified_resolved_pct | 29.2% |
| #7 | gemini-3-flash-preview Strong on Vals CorpFin v2 overall_accuracy_pct and Vals SWE-bench overall_accuracy_pct | 27.9% |
| #8 | claude-sonnet-4.6 Strong on Vals Finance Agent overall_accuracy_pct and Vals SWE-bench overall_accuracy_pct | 26.2% |
| #9 | Grok-4-0709 Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 25.8% |
| #10 | gpt-5.4-2026-03-05 Strong on Vals SWE-bench overall_accuracy_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 25.1% |
| #11 | claude-opus-4-5-20251101 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and FACTS Benchmark Suite facts_grounding_score_pct | 25.0% |
| #12 | claude-sonnet-4 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Galileo Agent Leaderboard v2 Avg AC | 24.9% |
| #13 | gemini-3.1-flash-lite-preview Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 24.5% |
| #14 | gpt-4.1-20250414 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Galileo Agent Leaderboard v2 Avg AC | 23.6% |
| #15 | o3-20250416 Strong on Aider Polyglot Leaderboard percent_correct_pct and SWE-bench Verified Leaderboard swe_verified_resolved_pct | 23.4% |
| #16 | gpt-5.1-2025-11-13 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 22.4% |
| #17 | grok-4-fast-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals LiveCodeBench overall_accuracy_pct | 20.3% |
| #18 | claude-opus-4-6-thinking Strong on Vals SWE-bench overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 20.2% |
| #20 | claude-opus-4-5-20251101-thinking Strong on Vals SWE-bench overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 18.9% |
| #21 | kimi-k2.5-thinking Strong on Vals CorpFin v2 overall_accuracy_pct and Vals LiveCodeBench overall_accuracy_pct | 18.5% |
| #22 | glm-5-thinking Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 17.3% |
| #24 | grok-4.20-0309-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals SWE-bench overall_accuracy_pct | 17.1% |
| #25 | claude-sonnet-4-5-20250929-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 17.0% |
| #26 | grok-4-1-fast-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 17.0% |
| #27 | Kimi K2 Thinking Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Vals CorpFin v2 overall_accuracy_pct | 16.7% |
| #28 | o4-mini Strong on Aider Polyglot Leaderboard percent_correct_pct and Vals LiveCodeBench overall_accuracy_pct | 16.6% |
| #29 | MiniMax-M2.7 Strong on Vals SWE-bench overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 16.3% |
| #30 | gemini-2.5-flash Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 15.5% |
| #31 | gpt-5.4-nano-2026-03-17 Strong on Vals LiveCodeBench overall_accuracy_pct and Vals SWE-bench overall_accuracy_pct | 15.5% |
| #32 | qwen3.5-flash Strong on Vals CorpFin v2 overall_accuracy_pct and Vals LiveCodeBench overall_accuracy_pct | 14.9% |
Compare Models
▶Ranking diagnostics & missing models
Source lift
Ranked
57
Sources
8
Quality
Good
Vals CorpFin v2
Vals LiveCodeBench
Vals Tax Eval v2
Vals Finance Agent
Missing frontier models
No obvious gaps right now.