BeyondAIME Original Effort: High 66.9% mistral.ai for Mistral Medium 3.5 (high) on BeyondAIME Original (opens in a new tab) Exact-answer accuracy Reported May 22, 2026 Launch post Mistral AI Self-reported Record for Mistral Medium 3.5 on BeyondAIME Original BrowseComp Effort: High 48.6% huggingface.co for Mistral Medium 3.5 (high) on BrowseComp BrowseComp (opens in a new tab) BrowseComp Accuracy Reported May 22, 2026 Model card Mistral AI Self-reported Record for Mistral Medium 3.5 on BrowseComp BrowseComp Finance Agent Benchmark 2 — October 2026 evaluation Effort: High 32.1% vals.ai for Mistral Medium 3.5 (high) on Finance Agent Benchmark 2 — October 2026 evaluation (opens in a new tab) Archived copy (opens in a new tab) Finance Agent Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Mistral Medium 3.5 on Finance Agent Benchmark 2 — October 2026 evaluation GPQA Diamond — Vals AI harness Effort: High Configuration: Vals AI harness: mean of zero-shot and few-shot CoT 34.8% vals.ai for Mistral Medium 3.5 (high) on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) GPQA Diamond Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Mistral Medium 3.5 on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness HLAB October 2026 evaluation Effort: High 0.4% vals.ai for Mistral Medium 3.5 (high) on Harvey's Legal Agent Benchmark October 2026 evaluation (opens in a new tab) Archived copy (opens in a new tab) HLAB Task Pass Rate Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Mistral Medium 3.5 on Harvey's Legal Agent Benchmark October 2026 evaluation IFBench Original Effort: High 68.0% huggingface.co for Mistral Medium 3.5 (high) on IFBench Original (opens in a new tab) Accuracy Reported May 22, 2026 Model card Mistral AI Self-reported Record for Mistral Medium 3.5 on IFBench Original MMLU-Pro Original — Vals AI harness Effort: High Configuration: Vals AI harness 75.3% vals.ai for Mistral Medium 3.5 (high) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Mistral Medium 3.5 on MMLU-Pro Original — Vals AI harness SWE-bench Verified Effort: High 77.6% huggingface.co for Mistral Medium 3.5 (high) on SWE-bench Verified (opens in a new tab) Resolved Tasks Reported May 22, 2026 Model card Mistral AI Self-reported Record for Mistral Medium 3.5 on SWE-bench Verified SWE-bench Verified — Vals AI mini-swe-agent Effort: High Configuration: mini-swe-agent harness 66.4% vals.ai for Mistral Medium 3.5 (high) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Mistral Medium 3.5 on SWE-bench Verified — Vals AI mini-swe-agent Terminal-Bench 2.0 — Vals AI Terminus 2 Effort: High Configuration: Terminus-2 harness 30.3% vals.ai for Mistral Medium 3.5 (high) on Terminal-Bench 2.0 — Vals AI Terminus 2 (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported June 4, 2026 Benchmark leaderboard Vals AI Independent Record for Mistral Medium 3.5 on Terminal-Bench 2.0 — Vals AI Terminus 2 Terminal-Bench 2.1 — Vals AI Terminus 2 Effort: High Configuration: Terminus-2 harness 39.0% vals.ai for Mistral Medium 3.5 (high) on Terminal-Bench 2.1 — Vals AI Terminus 2 (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported September 28, 2026 Benchmark leaderboard Vals AI Independent Record for Mistral Medium 3.5 on Terminal-Bench 2.1 — Vals AI Terminus 2 Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation Effort: High Configuration: OpenHands harness 2.9% vals.ai for Mistral Medium 3.5 (high) on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation (opens in a new tab) Archived copy (opens in a new tab) Vibe Code Bench Score Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Mistral Medium 3.5 on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation τ³-bench τ³ — Airline Effort: High 72.0% huggingface.co for Mistral Medium 3.5 (high) on τ³-bench τ³ — Airline (opens in a new tab) Task success rate Reported May 22, 2026 Model card Mistral AI Self-reported Record for Mistral Medium 3.5 on τ³-bench τ³ — Airline τ³-bench τ³ — Banking Effort: High 13.4% huggingface.co for Mistral Medium 3.5 (high) on τ³-bench τ³ — Banking (opens in a new tab) Task success rate Reported May 22, 2026 Model card Mistral AI Self-reported Record for Mistral Medium 3.5 on τ³-bench τ³ — Banking τ³-bench τ³ — Retail Effort: High 76.1% huggingface.co for Mistral Medium 3.5 (high) on τ³-bench τ³ — Retail (opens in a new tab) Task success rate Reported May 22, 2026 Model card Mistral AI Self-reported Record for Mistral Medium 3.5 on τ³-bench τ³ — Retail τ³-bench τ³ — Telecom Effort: High 91.4% huggingface.co for Mistral Medium 3.5 (high) on τ³-bench τ³ — Telecom (opens in a new tab) Task success rate Reported May 22, 2026 Model card Mistral AI Self-reported Record for Mistral Medium 3.5 on τ³-bench τ³ — Telecom