# Claude Sonnet 4.6 vs Mistral Medium 3.5 128B > Side-by-side benchmark comparison for Claude Sonnet 4.6 and Mistral Medium 3.5 128B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks. - Canonical page: https://benchlm.ai/compare/claude-sonnet-4-6-vs-mistral-medium-3-5-128b - Last updated: September 10, 2026 - Shared sourced benchmarks: 6 - HTML indexing: indexable - Ranking lane: BenchAlign v5 ## Quick Verdict Pick Claude Sonnet 4.6 if you want the stronger benchmark profile. Mistral Medium 3.5 128B only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score. ## Summary - Claude Sonnet 4.6 leads overall 62.96 to 30.13. - The clearest category separation is in instruction following, where the averages are 48.2 for Claude Sonnet 4.6 and 84 for Mistral Medium 3.5 128B. - The biggest single benchmark swing is GPQA Diamond (Vals) in Knowledge, with scores of 85.6% and 34.8%. - Mistral Medium 3.5 128B is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use. - Mistral Medium 3.5 128B also has the larger context window at 256K. ## Model Snapshot | Property | Claude Sonnet 4.6 | Mistral Medium 3.5 128B | |----------|----------|----------| | Creator | Anthropic | Mistral | | Type | Proprietary | Open Weight | | Reasoning | Non-Reasoning | Reasoning | | Context | 200K | 256K | | Overall Score | 62.96 | 30.13 | | Benchmarks Covered | 25 | 7 | | Pricing (input/output) | $3.00 / $15.00 | $1.50 / $7.50 | ## Category Breakdown ### Agentic - Winner: Claude Sonnet 4.6 - Claude Sonnet 4.6 public-lane score: 44 (Supported · #93/152) - Mistral Medium 3.5 128B public-lane score: 21.9 (Supported · #150/152) | Benchmark | Claude Sonnet 4.6 | Mistral Medium 3.5 128B | Winner | |-----------|-----------|-----------|--------| | Terminal-Bench 2.0 | 59.1% | Coming soon | Coming soon | | OSWorld-Verified | 72.1% | Coming soon | Coming soon | | Claw-Eval | 67.8% | Coming soon | Coming soon | | CyberGym | 65.2% | Coming soon | Coming soon | | Gert Labs | 62.92% | 39.10% | Claude Sonnet 4.6 | | OSWorld 2.0 | 8.3% | Coming soon | Coming soon | | JobBench | 36.9% | Coming soon | Coming soon | | Terminal-Bench 2.1 (Vals) | 57.3% | 39.0% | Claude Sonnet 4.6 | | τ³-bench results | Coming soon | 91.4% | Coming soon | ### Coding - Winner: Coming soon - Claude Sonnet 4.6 public-lane score: 52.2 (Supported · #48/151) - Mistral Medium 3.5 128B public-lane score: 36.9 (Estimated · #127/151) | Benchmark | Claude Sonnet 4.6 | Mistral Medium 3.5 128B | Winner | |-----------|-----------|-----------|--------| | SWE-bench Verified | 79.6% | 77.6% | Claude Sonnet 4.6 | | SWE-Rebench | 60.7% | Coming soon | Coming soon | | React Native Evals | 80.6% | Coming soon | Coming soon | | Vibe Code Bench | 51.48% | Coming soon | Coming soon | | cursorBench31 | 48.8% | Coming soon | Coming soon | | FrontierCode 1.1 Main | 24.3% | Coming soon | Coming soon | | LiveCodeBench (Vals) | 82.1% | Coming soon | Coming soon | | SWE-bench (Vals) | 77.4% | 66.4% | Claude Sonnet 4.6 | ### Multimodal & Grounded - Winner: Coming soon - Claude Sonnet 4.6 public-lane score: 54.1 (#33/48) - Mistral Medium 3.5 128B public-lane score: 55.6 (Unranked · 1 rankable row) | Benchmark | Claude Sonnet 4.6 | Mistral Medium 3.5 128B | Winner | |-----------|-----------|-----------|--------| | CharXiv | 77.4% | Coming soon | Coming soon | ### Reasoning - Winner: Coming soon - Claude Sonnet 4.6 public-lane score: 67.9 (Unranked · 2 rankable rows) - Mistral Medium 3.5 128B public-lane score: 68.6 (Unranked · 2 rankable rows) ### Knowledge - Winner: Claude Sonnet 4.6 - Claude Sonnet 4.6 public-lane score: 55.8 (Supported · #51/183) - Mistral Medium 3.5 128B public-lane score: 39 (Supported · #140/183) | Benchmark | Claude Sonnet 4.6 | Mistral Medium 3.5 128B | Winner | |-----------|-----------|-----------|--------| | GPQA | 89.9% | Coming soon | Coming soon | | SuperGPQA | 95% | Coming soon | Coming soon | | MMLU-Pro | 79.2% | Coming soon | Coming soon | | HLE | 49% | Coming soon | Coming soon | | GPQA Diamond (Vals) | 85.6% | 34.8% | Claude Sonnet 4.6 | | MMLU-Pro (Vals) | 87.3% | 75.3% | Claude Sonnet 4.6 | ### Instruction Following - Winner: Coming soon - Claude Sonnet 4.6 public-lane score: 48.2 (#86/123) - Mistral Medium 3.5 128B public-lane score: 84 (#48/123) ### Mathematics - Winner: Coming soon - Claude Sonnet 4.6 public-lane score: 49 (Unranked · 2 rankable rows) - Mistral Medium 3.5 128B public-lane score: Coming soon | Benchmark | Claude Sonnet 4.6 | Mistral Medium 3.5 128B | Winner | |-----------|-----------|-----------|--------| | FrontierMath v2 (Tiers 1-3) | 32.400% | Coming soon | Coming soon | | FrontierMath v2 (Tier 4) | 8.300% | Coming soon | Coming soon | ## FAQ ### Which is better overall, Claude Sonnet 4.6 or Mistral Medium 3.5 128B? Claude Sonnet 4.6 is ahead overall on BenchLM right now. ### Where is the biggest gap between Claude Sonnet 4.6 and Mistral Medium 3.5 128B? The widest category gap is in instruction following, where the averages are 48.2 for Claude Sonnet 4.6 and 84 for Mistral Medium 3.5 128B. ### How many benchmarks does Claude Sonnet 4.6 cover on BenchLM? Claude Sonnet 4.6 currently has 25 sourced benchmark scores on BenchLM. ### How many benchmarks does Mistral Medium 3.5 128B cover on BenchLM? Mistral Medium 3.5 128B currently has 7 sourced benchmark scores on BenchLM. ## Related Comparisons - [Claude Sonnet 4.6 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-claude-sonnet-4-6) - [Mistral Medium 3.5 128B vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-mistral-medium-3-5-128b) - [Claude Sonnet 4.6 vs GPT-6 Astra](/compare/claude-sonnet-4-6-vs-gpt-6-astra) - [Mistral Medium 3.5 128B vs GPT-6 Astra](/compare/gpt-6-astra-vs-mistral-medium-3-5-128b) ## Explore More - [Claude Sonnet 4.6 profile](/models/claude-sonnet-4-6) - [Mistral Medium 3.5 128B profile](/models/mistral-medium-3-5-128b) - [Compare Pricing](/llm-pricing) - [Alternative Finder](/tools/alternative-finder) - [LLM Selector](/tools/llm-selector) - [Overall Rankings](/best/overall)