Shift handover summary
Summarize shift notes into incidents, actions, and open items.
Provisional leader
gpt-4.1-20250414
Current leader based on limited benchmark evidence. Treat this ranking as directional until coverage improves.
20.5%
Best benchmark score
30.3%
Confidence
All ranked models — top 3
Ranked Models
30
Evidence Quality
79%
Evidence Points
18
Top Signal
MMLongBench-Doc Leaderboard: acc_score_pct
All Ranked Models
| Rank | Model | Score |
|---|---|---|
| 🥇 | gpt-4.1-20250414 Strong on MMLongBench-Doc Leaderboard acc_score_pct and Galileo Agent Leaderboard v2 Avg TSQ | 20.5% |
| 🥈 | gemini-2.5-pro Strong on Galileo Agent Leaderboard v2 Avg TSQ and SciArena Leaderboard rating_elo | 17.0% |
| 🥉 | gpt-5-2025-08-07 Strong on SciArena Leaderboard rating_elo and Aider Polyglot Leaderboard percent_correct_pct | 16.9% |
| #4 | claude-sonnet-4 Strong on Galileo Agent Leaderboard v2 Avg TSQ and Galileo Agent Leaderboard v2 Avg AC | 16.6% |
| #5 | Grok-4-0709 Strong on Galileo Agent Leaderboard v2 Avg TSQ and Galileo Agent Leaderboard v2 Avg AC | 15.7% |
| #6 | qwen-2.5-72b-instruct Strong on Galileo Agent Leaderboard v2 Avg TSQ and DuckDB NSQL Leaderboard all_execution_accuracy | 15.0% |
| #7 | gemini-3-pro-preview Strong on SciArena Leaderboard rating_elo and BFCL Multi-turn Official Multi Turn Acc | 14.2% |
| #8 | gpt-4o Strong on MEGA-Bench app:Planning and JSONSchemaBench Leaderboard medium_schema_compliance_pct | 14.0% |
| #9 | gpt-5-mini-2025-08-07 Strong on SciArena Leaderboard rating_elo and Vals MedQA overall_accuracy_pct | 13.9% |
| #10 | o3-20250416 Strong on SciArena Leaderboard rating_elo and Aider Polyglot Leaderboard percent_correct_pct | 13.9% |
| #11 | gemini-2.5-flash Strong on Galileo Agent Leaderboard v2 Avg TSQ and Galileo Agent Leaderboard v2 Avg AC | 13.6% |
| #12 | gpt-4o-20241120 Strong on MMLongBench-Doc Leaderboard acc_score_pct and DuckDB NSQL Leaderboard all_execution_accuracy | 13.0% |
| #13 | gemini-3.1-pro-preview Strong on Vals Mortgage Tax overall_accuracy_pct and Vals GPQA overall_accuracy_pct | 13.0% |
| #14 | gpt-5.2-2025-12-11 Strong on BFCL Multi-turn Official Multi Turn Acc and FACTS Benchmark Suite facts_grounding_score_pct | 11.8% |
| #15 | claude-sonnet-4.6 Strong on HalluHard Leaderboard overall_hallucination_error_pct and Vals Tax Eval v2 overall_accuracy_pct | 10.6% |
| #16 | gemini-3-flash-preview Strong on Vals Legal Bench overall_accuracy_pct and Vals MedQA overall_accuracy_pct | 10.5% |
| #18 | o4-mini Strong on SciArena Leaderboard rating_elo and Aider Polyglot Leaderboard percent_correct_pct | 10.1% |
| #19 | gpt-5.4-2026-03-05 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Vals MedQA overall_accuracy_pct | 9.9% |
| #20 | Claude-3.5-Sonnet Strong on DuckDB NSQL Leaderboard all_execution_accuracy and LLM-AggreFact Leaderboard average_score_pct | 9.7% |
| #21 | gpt-5.1-2025-11-13 Strong on Vals Case Law v2 overall_accuracy_pct and Vals MedScribe overall_accuracy_pct | 9.6% |
| #22 | deepseek-r1 Strong on DuckDB NSQL Leaderboard all_execution_accuracy and SciArena Leaderboard rating_elo | 9.5% |
| #23 | gpt-4o-mini-2024-07-18 Strong on LLM Trustworthy Leaderboard privacy and DuckDB NSQL Leaderboard all_execution_accuracy | 9.4% |
| #24 | claude-opus-4-5-20251101 Strong on Vals Mortgage Tax overall_accuracy_pct and Vals MedQA overall_accuracy_pct | 9.3% |
| #25 | gpt-4.1-mini-20250414 Strong on Galileo Agent Leaderboard v2 Avg TSQ and Galileo Agent Leaderboard v2 Avg AC | 9.3% |
| #26 | grok-4-1-fast-reasoning Strong on BFCL Multi-turn Official Multi Turn Acc and Vals CorpFin v2 overall_accuracy_pct | 9.1% |
| #27 | claude-opus-4-6-thinking Strong on Vals SWE-bench overall_accuracy_pct and Vals Mortgage Tax overall_accuracy_pct | 9.0% |
| #28 | gpt-4o-2024-05-13 Strong on LLM Trustworthy Leaderboard privacy and LLM-AggreFact Leaderboard rag_truth_score_pct | 8.9% |
| #29 | Kimi-K2-Instruct Strong on Galileo Agent Leaderboard v2 Avg TSQ and Galileo Agent Leaderboard v2 Avg AC | 8.9% |
| #30 | claude-opus-4-5-20251101-thinking Strong on Vals MedQA overall_accuracy_pct and Vals Mortgage Tax overall_accuracy_pct | 8.8% |
| #31 | gemini-3.1-flash-lite-preview Strong on Vals Mortgage Tax overall_accuracy_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 8.7% |
Compare Models
▶Ranking diagnostics & missing models
Source lift
Ranked
51
Sources
8
Quality
Low
Vals Legal Bench
Vals CorpFin v2
Vals MedQA
Vals Tax Eval v2
Missing frontier models
No obvious gaps right now.