Mistral Large 4 Preview · Intelligence Index v5.0 ↗
1 more reported result
38.38 index · Mistral Large 4 Preview · Intelligence Index v4.3.2 · Artificial Analysis ↗
Mistral / MODEL EVIDENCE
Mistral Large 4 Preview
22 benchmarks · 26 observations · 20 sources · released 2026-10-06
Scores at a glance
22 benchmarks · large dot: Mistral Large 4 Preview; small dots: closest models where reported
AA-Briefcase v1.1 ↗1390.80 Elo
Mistral Large 4 Preview · AA-Briefcase v1.1 · overall Elo ↗
AutomationBench-AA ↗59.90%
Mistral Large 4 Preview · AutomationBench-AA · guardrail-gated objective score ↗
GDP.pdf ↗18.60%
Mistral Large 4 Preview · GDP.pdf · all-pass ↗
Terminal-Bench 4.0 ↗26.77%
Mistral Large 4 Preview · Terminal-Bench 4.0 · AA harness ↗
Mistral Large 4 Preview · Terminal-Bench-Science 0.1 · AA harness ↗
FrontierCode 2.0 ↗13.58%
Mistral Large 4 Preview · FrontierCode 2.0 · AA implementation ↗
Mistral Large 4 Preview · CritPt v2 · hard subset · AA implementation ↗
HLE-Diamond ↗15.10%
Mistral Large 4 Preview · HLE-Diamond · AA implementation ↗
AA-Omniscience v1.1 ↗-7.50 index
Mistral Large 4 Preview · AA-Omniscience v1.1 · error-penalized index ↗
1 more reported result
-5.30 index · Mistral Large 4 Preview · AA-Omniscience · error-penalized score · Artificial Analysis ↗
Mistral Large 4 Preview · AA-Omniscience v1.1 · accuracy ↗
1 more reported result
25.82% · Mistral Large 4 Preview · AA-Omniscience · accuracy · Artificial Analysis ↗
Mistral Large 4 Preview · AA-Omniscience v1.1 · hallucination rate, lower is better ↗
1 more reported result
41.95% · Mistral Large 4 Preview · AA-Omniscience · hallucination rate, lower is better · Artificial Analysis ↗
GDPval-AA v2.1 ↗1421.88 Elo
Mistral Large 4 Preview · GDPval-AA v2.1 · Elo ↗
AA-3D ↗870.16 Elo
Mistral Large 4 Preview · AA-3D · Elo ↗
Harvey LAB-AA v1.1 ↗3.06%
Mistral Large 4 Preview · Harvey LAB-AA v1.1 · all-pass ↗
FrontierCode 1.1 ↗41.53%
Mistral Large 4 Preview · FrontierCode 1.1 · AA implementation ↗
AA-LCR v1.1 ↗81.33%
Mistral Large 4 Preview · AA-LCR v1.1 ↗
SciCode ↗54.17%
Mistral Large 4 Preview · SciCode · AA implementation ↗
Humanity’s Last Exam ↗35.03%
Mistral Large 4 Preview · Humanity’s Last Exam · AA implementation ↗
MMMU-Pro ↗76.42%
Mistral Large 4 Preview · MMMU-Pro · AA implementation ↗
MLCR-AA ↗7.78%
Mistral Large 4 Preview · MLCR-AA · overall ↗
CritPt ↗10.57%
Mistral Large 4 Preview · CritPt · original ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
Qwen3.8 27B →Qwen
19 of 21 shared benchmark comparisons
18 of 21 shared benchmark comparisons
18 of 21 shared benchmark comparisons
How similarity is measured
Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
- AA-3D: Interactive 3D Experience Benchmark | Artificial Analysis ↗
- AA-Briefcase v1.1: Agentic Knowledge Work Benchmark | Artificial Analysis ↗
- Artificial Analysis Intelligence Index v5.0 — Artificial Analysis ↗
- AA-LCR v1.1: Long Context Reasoning Benchmark | Artificial Analysis ↗
- AutomationBench-AA: Agentic SaaS Workflow Benchmark | Artificial Analysis ↗
- CritPt Benchmark | Artificial Analysis ↗
- CritPt v2 — Hard Subset — Artificial Analysis ↗
- FrontierCode 1.1 Benchmark | Artificial Analysis ↗
- FrontierCode 2.0 Benchmark — Artificial Analysis ↗
- GDP.pdf Benchmark | Artificial Analysis ↗
- GDPval-AA v2.1 Benchmark | Artificial Analysis ↗
- Harvey LAB-AA v1.1 Benchmark | Artificial Analysis ↗
- HLE-Diamond Benchmark — Artificial Analysis ↗
- Humanity's Last Exam Benchmark | Artificial Analysis ↗
- MLCR-AA: Medical Long Context Reasoning Benchmark | Artificial Analysis ↗
- MMMU-Pro Benchmark | Artificial Analysis ↗
- AA-Omniscience v1.1: Knowledge and Hallucination Benchmark — Artificial Analysis ↗
- SciCode Benchmark | Artificial Analysis ↗
- Terminal-Bench-Science 0.1 Benchmark | Artificial Analysis ↗
- Terminal-Bench 4.0 Benchmark | Artificial Analysis ↗
Names used in source tables
Mistral Large 4 Preview