RankingMistral Large 4
Mistral Large 4
Mistral Large 4 by Mistral is a Mistral Large model, released 2026-10-06. This profile collects the published benchmark results and reported effort settings for this model. Configurations are compared on the effort page. Ranks are on the leaderboard.
26 published benchmark measures · 64 measured effort results · 3 benchmark families contribute across 3 task areas. 2 capability estimates available in the full profile. See all results ↓ · Compare published benchmarks →
Model evidence summary
This profile combines published settings. It is not a runnable configuration or a leaderboard rank. Compare measured configurations →
Performance profile
Capabilities
Filled points are supported; hollow points are preliminary. Lines stop at unknown capabilities. Exact values and sources follow below.
Scores estimate outcomes against a shared reference panel; they are not accuracy percentages. Sparse or disconnected evidence cannot qualify an overall profile. Open a capability to inspect its evidence.
Reported effort · Not specified
Settings reported in this model's published benchmark results, including results outside the aggregate. Effort names are provider-specific. These are not API defaults or equal compute budgets.
- Not specified: 28 observations
Mixed settings means multiple settings occur in the evidence. Best across efforts means the source selected its best reported result across settings; it does not mean Max. Unspecified settings stay unknown. This model-summary chart combines reported settings. The leaderboard keeps identified configurations separate and excludes unknown effort.
Inspect each result and its source ↓ · Download effort evidenceScore contributions and missing evidence
3 contributing families across 3 capabilities. Fixed reference panels do not change when the catalog expands.
Capability is fitted jointly across families. Capability estimates below describe different task areas; their weighted sum is not the Capability score.
Results without reviewed compatibility or a reference match remain in the raw evidence below. Coverage counts only contributing results.
Model information & shareable badge
- Lab
- Mistral
- Catalog status
- preview
- Availability
- Public preview API on Mistral Studio. Open weights promised by end of October 2026; weights and license are not yet established.
- Family
- Mistral Large
- Released
- 2026-10-06
- Context
- 1,000,000 tokens
- API list price
- $1.36 input / $4.18 output per million tokens
- License
- —
- Model card
- https://docs.mistral.ai/models/mistral-large-4-0
- Default Capability family coverage
/badge/mistral-large-4.svg
Mistral Large 4 measured results by effort setting
Each row is one published result for one effort setting. Evidence collected 2026-11-22. Compare the effort settings →
| Benchmark | Effort | Score | Source |
|---|---|---|---|
| AA-Briefcase Elo | High | 1347 | Artificial Analysis |
| AA-Briefcase Elo | Medium | 1187 | Artificial Analysis |
| AA-Briefcase Elo | Reasoning | 1393 | Artificial Analysis |
| AA-LCR v1.1 | Reasoning | 81.3% | Artificial Analysis |
| AA-Omniscience Accuracy | High | 26.0% | Artificial Analysis |
| AA-Omniscience Accuracy | Medium | 22.5% | Artificial Analysis |
| AA-Omniscience Accuracy | Reasoning | 23.9% | Artificial Analysis |
| AA-Omniscience Index | High | 5.1 | Artificial Analysis |
| AA-Omniscience Index | Medium | 3.3 | Artificial Analysis |
| AA-Omniscience Index | Reasoning | -7.5 | Artificial Analysis |
| Artificial Analysis Cyber Index | Unspecified | 49.5 | Artificial Analysis |
| AutomationBench-AA | High | 57.8% | Artificial Analysis |
| AutomationBench-AA | Medium | 52.8% | Artificial Analysis |
| AutomationBench-AA | Reasoning | 59.9% | Artificial Analysis |
| CritPt | High | 10.0% | Artificial Analysis |
| CritPt | Medium | 11.1% | Artificial Analysis |
| CritPt | Reasoning | 10.6% | Artificial Analysis |
| GDP.pdf: All-pass Rate | High | 17.6% | Artificial Analysis |
| GDP.pdf: All-pass Rate | Medium | 16.8% | Artificial Analysis |
| GDP.pdf: All-pass Rate | Reasoning | 18.6% | Artificial Analysis |
| GDPval-AA v2.1 Leaderboard | Reasoning | 1431 | Artificial Analysis |
| Harvey LAB-AA v1.1: Hallucination-Gated All-Pass Rate | Reasoning | 3.1% | Artificial Analysis |
| Humanity's Last Exam | Reasoning | 35.0% | Artificial Analysis |
| LiveBench · AMPS Hard · 2026-06-25 | High | 98.0% | LiveBench |
| LiveBench · code completion · 2026-06-25 | High | 78.3% | LiveBench |
| LiveBench · code generation · 2026-06-25 | High | 76.1% | LiveBench |
| LiveBench · connections · 2026-06-25 | High | 48.0% | LiveBench |
| LiveBench · consecutive events · 2026-06-25 | High | 80.5% | LiveBench |
| LiveBench · integrals with game · 2026-06-25 | High | 90.0% | LiveBench |
| LiveBench · javascript · 2026-06-25 | High | 68.2% | LiveBench |
| LiveBench · logic with navigation · 2026-06-25 | High | 68.0% | LiveBench |
| LiveBench · math comp · 2026-06-25 | High | 97.1% | LiveBench |
| LiveBench · olympiad · 2026-06-25 | High | 89.3% | LiveBench |
| LiveBench · paraphrase · 2026-06-25 | High | 64.0% | LiveBench |
| LiveBench · plot unscrambling · 2026-06-25 | High | 40.9% | LiveBench |
| LiveBench · python · 2026-06-25 | High | 60.0% | LiveBench |
| LiveBench · simplify · 2026-06-25 | High | 66.2% | LiveBench |
| LiveBench · spatial · 2026-06-25 | High | 94.0% | LiveBench |
| LiveBench · story generation · 2026-06-25 | High | 67.5% | LiveBench |
| LiveBench · summarize · 2026-06-25 | High | 61.6% | LiveBench |
| LiveBench · tablejoin · 2026-06-25 | High | 49.1% | LiveBench |
| LiveBench · tablereformat · 2026-06-25 | High | 100.0% | LiveBench |
| LiveBench · theory of mind · 2026-06-25 | High | 80.8% | LiveBench |
| LiveBench · typescript · 2026-06-25 | High | 43.3% | LiveBench |
| LiveBench · typos · 2026-06-25 | High | 60.0% | LiveBench |
| LiveBench · zebra puzzle · 2026-06-25 | High | 93.0% | LiveBench |
| MLCR-AA | High | 17.8% | Artificial Analysis |
| MLCR-AA | Reasoning | 7.8% | Artificial Analysis |
| MMMU-Pro | Reasoning | 76.4% | Artificial Analysis |
| SciCode | Reasoning | 54.2% | Artificial Analysis |
| sudo L7 | High | 11.7% | Surge AI |
| Terminal-Bench 4.0 · claudecode | Max | 27.9% | Terminal-Bench |
| Terminal-Bench v4.0 | High | 24.7% | Artificial Analysis |
| Terminal-Bench v4.0 | Medium | 23.2% | Artificial Analysis |
| Terminal-Bench v4.0 | Reasoning | 26.8% | Artificial Analysis |
| Terminal-Bench-Science 0.1 | High | 4.3% | Artificial Analysis |
| Terminal-Bench-Science 0.1 | Medium | 3.3% | Artificial Analysis |
| Terminal-Bench-Science 0.1 | Reasoning | 4.8% | Artificial Analysis |
| Vals AI · Code Migration v1 | High | 30.6% | Vals AI |
| Vals AI · Excel Modeling Benchmark v1 | High | 56.2% | Vals AI |
| Vals AI · Finance Agent v2 | High | 54.7% | Vals AI |
| Vals AI · Legal Research Bench v1 | High | 31.7% | Vals AI |
| Vals AI · Tax Agent Bench v1: Weighted Pass | High | 63.3% | Vals AI |
| Vals AI · Vibe Code Bench v1.1 | High | 78.4% | Vals AI |
Benchmark scores & sources
Original results, evaluation harnesses, and evidence behind this model.
| Benchmark | Bucket | Score | Harness | Evidence | Source-recorded date |
|---|---|---|---|---|---|
| SWE-Atlas-QnA | Supporting evidence | 59.4%Reported settings & sourcePublic Mistral Large4 Preview. Effort, sampling and evaluation budgets are not stated. Chart footnote attributes private Artificial Analysis evaluation before public harness launch; provider-republished claim, not a new independent result. Provider-published lab_self_report; retained as launch evidence, not an independent board admission. Narrative states59.4%; chart rounds to59. Exact printed chart label; asset https://mistral.ai/_astro/code-benchmarks---swe-atlas-qna-v3_2wiWq0.webp?dpl=6ac6a8353c2a68969e300fd2; asset SHA256 9f9d32e5c05b99d91047ead47225644319e95ed3ff0e51415c10681bffbb8d56. Comparison limit: Provider publication; exact benchmark-specific configuration and independent evaluation provenance require separate review before matched-board admission. Introducing Mistral Large 4 — public preview · Capabilities deep-dive; SWE-Atlas-QnA; chart 10 (mistral-chart-10.webp) · reviewed 2026-10-07 | Published configuration | lab self-report | Reviewed 2026-10-07 |
| Terminal-Bench · 4.0 | Coding | 28.3%Reported settings & sourcePublic Mistral Large4 Preview. Effort, sampling and evaluation budgets are not stated. Chart footnote attributes private Artificial Analysis evaluation before public harness launch; provider-republished claim, not a new independent result. Provider-published lab_self_report; retained as launch evidence, not an independent board admission. Narrative states28.3%; chart rounds to28. Exact printed chart label; asset https://mistral.ai/_astro/code-benchmarks---terminal-bench-4%201-v3_Z2iGo8O.webp?dpl=6ac6a8353c2a68969e300fd2; asset SHA256 c3201abcd5c42890988e41c33719804fe09ff7ffe90bd0c71553e964a1f4d340. Comparison limit: Provider publication; exact benchmark-specific configuration and independent evaluation provenance require separate review before matched-board admission. Introducing Mistral Large 4 — public preview · Capabilities deep-dive; Terminal-Bench; chart 1 (mistral-chart-1.webp) · reviewed 2026-10-07 | Published configuration | lab self-report | Reviewed 2026-10-07 |
| Terminal-Bench 4.0 | Coding | 27.88% | Terminal-Bench 4.0 reportedcontributes to capability | official board | 2026-10-06 |
| ARC-AGI-2 | Hard reasoning | — | — | — | — |
| DeepSWE v1.1 | Agentic | — | — | — | — |
| GPQA Diamond | Hard reasoning | — | — | — | — |
| Humanity's Last Exam | Hard reasoning | — | — | — | — |
| LiveCodeBench | Coding | — | — | — | — |
| MMLU-Pro | Knowledge | — | — | — | — |
| OSWorld-Verified | Agentic | — | — | — | — |
| SWE-bench Pro | Agentic | — | — | — | — |
| SWE-bench Verified | Agentic | — | — | — | — |
| Terminal-Bench 2.1 | Agentic | — | — | — | — |