RankingEffort benchmarks

Mistral Large 4

Compare models

42 measured results · 2 effort settings · 42 benchmark/harness combinations

Model evidence and sources →

Change model

Model

Current configurationSources

Compare with

Choose a second model and its effort to see both profiles and benchmark differences below.

Compare withModel and configuration

Capability profile

One configuration, seven capabilities

Comparison score · 0–100

AMistral Large 4 · Reasoning2 of 7 capabilities supported

Gaps are unknown, not zero. Hollow points are preliminary.

Agentic
A57.6Supported
Hard reasoning
A34.5Supported
Coding
A67.3Preliminary
Human pref
Unknown
Knowledge
A14.4Preliminary
Multimodal
A28.7Preliminary
Long context
A59.8Preliminary

Each profile belongs to the named configuration. Capability scores use a shared panel for all axes, distinct from the overall ranking panel; they are not accuracy percentages or direct head-to-head wins.

Capability score evidence

Mistral Large 4 · Reasoning: 35.9 overall comparison score. Meets the overall evidence requirements.

6 areas measured. The available task mix affects this estimate; missing areas remain unknown.

Shared-result disagreement. This aggregate order conflicts with matched benchmark results against 1 other configurations. Different test coverage and opponents affect the fit. Inspect published results before treating the rank as conclusive.

Which sources carry the weight?

Artificial Analysis · 100.0% direct comparison weight · independent of the model provider

Which benchmark families carry the weight?

Humanity’s Last Exam · 11.9% direct comparison weight
Critpt · 11.8% direct comparison weight
omniscience · 11.7% direct comparison weight
Mmmu Pro · 11.5% direct comparison weight
Aa Lcr · 10.9% direct comparison weight
Other families (5) · 42.2% direct comparison weight

These shares describe direct comparison weight, not fractions of the final score or confidence. Source balancing does not give every family equal weight or remove correlations between overlapping sources.

How sensitive is this score?

The audit removes one source at a time and refits against the same overall reference panel. These published results use the matching dataset audited 2026-10-08.

Both ranks use the same surviving configurations for each removal. The cohort starts with 444 configurations supported in the original audit, including separate effort settings. These are diagnostic positions, not the default leaderboard ranks. Eligibility is not rechecked after removal.

What changes when a source is removed?
Removed source	Rank before → after	Rank movement	Cohort remaining / lost support	Score after (change)
Artificial Analysis	Comparison support lost; no rank		204 remaining / 240 lost	Unavailable
ARC Prize	96 → 89	Up 7	444 remaining / 0 lost	41.8 (+5.9 points)
Datacurve	96 → 94	Up 2	444 remaining / 0 lost	31.8 (-4.1 points)
LiveCodeBench	96 → 96	No movement	444 remaining / 0 lost	35.8 (-0.1 points)
Scale	96 → 94	Up 2	444 remaining / 0 lost	38.0 (+2.1 points)
Terminal-Bench	96 → 99	Down 3	444 remaining / 0 lost	36.0 (+0.1 points)
Cognition	96 → 97	Down 1	444 remaining / 0 lost	34.9 (-1.0 points)
LiveBench	96 → 94	Up 2	443 remaining / 1 lost	36.8 (+0.9 points)
SWE-rebench	96 → 95	Up 1	444 remaining / 0 lost	36.1 (+0.2 points)
Epoch AI	94 → 98	Down 4	426 remaining / 18 lost	36.4 (+0.5 points)
Vals AI	96 → 96	No movement	443 remaining / 1 lost	34.8 (-1.1 points)
Provider reports · Anthropic	96 → 96	No movement	444 remaining / 0 lost	35.9 (-0.0 points)
Provider reports · Moonshot AI	96 → 96	No movement	444 remaining / 0 lost	35.4 (-0.5 points)
Provider reports · Meta	96 → 96	No movement	444 remaining / 0 lost	35.8 (-0.1 points)
Provider reports · Mistral	96 → 96	No movement	444 remaining / 0 lost	35.9 (+0.0 points)
Provider reports · OpenAI	96 → 96	No movement	444 remaining / 0 lost	36.1 (+0.2 points)
All provider reports	96 → 96	No movement	444 remaining / 0 lost	35.6 (-0.3 points)

Lost support means a configuration no longer has a comparison path to the complete reference panel. Its rank is unavailable. A surviving path alone does not establish leaderboard eligibility.

Overlapping sources may remain correlated even with source balancing. Leave-one-source-out movement is a sensitivity diagnostic, not a spread of source-specific ranks or a confidence measure. Scoring methodology · Dated configuration audit

Every benchmark family

Removed evidence	Recomputed score	Change
omniscience	42.7	+6.8
arc-agi	41.0	+5.2
deepswe	31.8	-4.0
automationbench	32.3	-3.6
mmmu-pro	39.4	+3.5
hle	38.1	+2.2
briefcase	34.1	-1.8
terminal-bench	34.7	-1.2
aa-lcr	34.7	-1.2
gdp-pdf	34.9	-1.0
frontiercode	34.9	-1.0
gdpval	34.9	-1.0
epoch-game-puzzles	34.9	-1.0
critpt	36.8	+1.0
simpleqa	36.8	+0.9
ifbench	35.2	-0.6
arc-agi-3	35.4	-0.5
livebench-instructions	36.3	+0.4
multi-swe-bench	35.5	-0.4
mmlu-pro	36.2	+0.3
tau-bench	35.6	-0.3
livebench-language	36.2	+0.3
apex-agents	36.2	+0.3
terminal-bench-science	36.2	+0.3
swe-atlas-qna	35.6	-0.3
gpqa	35.6	-0.3
enigma-eval	36.1	+0.3
livecodebench	35.7	-0.2
livebench-coding	35.7	-0.2
aime	35.7	-0.2
swe-rebench	36.1	+0.2
harvey	35.7	-0.2
analyst-agent	36.0	+0.1
vibe-code	35.7	-0.1
livebench-reasoning	35.8	-0.1
swe-atlas-test-writing	35.8	-0.1
frontiermath	36.0	+0.1
enterprise-ops	36.0	+0.1
vals-finance-agent	35.8	-0.1
vals-legal-research	35.8	-0.1
math500	35.8	-0.1
vals-code-migration	35.8	-0.1
vals-tax-agent	35.8	-0.1
swe-atlas-refactoring	35.8	-0.0
itbench	35.8	-0.0
vals-excel-modeling	35.9	-0.0
gmmlu	35.9	+0.0
livebench-math	35.9	+0.0
livebench-data	35.9	+0.0
swe-bench-pro	35.9	+0.0

What evidence is missing from the fit?

Across all collected settings for this model: 62 observations, 10 contributing, 0 matched without graph weight and 52 excluded. Counts do not establish rank eligibility.

1 · Benchmark family or source protocol has not been reviewed
1 · Original SciCode grading defects are under review; retained as supporting evidence, excluded from aggregate and capability scores. Corrected SciCode-Verified requires a separate protocol review. Sources: https://arxiv.org/abs/2608.04975 and https://artificialanalysis.ai/evaluations/scicode
23 · LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label.
7 · Vals reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label.
18 · Provider publication; exact benchmark-specific configuration and independent evaluation provenance require separate review before matched-board admission.
1 · Supporting evidence outside the reviewed capability core
1 · No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately

Inspect every observation and exclusion →

Benchmark results

These are published benchmark scores. Supported effort estimates also appear on the Capability leaderboard. Results from different harnesses occupy different rows. Missing cells stay unknown; no scores are copied between effort levels.

Benchmark / source	High	Reasoning
AA-Briefcase EloArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details AA-Briefcase v1.1 is an agentic knowledge work benchmark developed by Artificial Analysis. AA-Briefcase Elo is a combined metric that aggregates rubric pass rate, analytical quality Elo and presentation Elo · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-10-08.	Not reported	1,392.53 Elo Reported settings Mistral Large 4 Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-4; Mode from evaluator isReasoning metadata; effort budget not specified
AA-LCR v1.1Artificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-08.	Not reported	81.33% Reported settings Mistral Large 4 Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-4; Mode from evaluator isReasoning metadata; effort budget not specified
AutomationBench-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of task objectives completed with no guardrail violations · Higher is better · Benchmark developed by Zapier · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-08.	Not reported	59.9% Reported settings Mistral Large 4 Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-4; Mode from evaluator isReasoning metadata; effort budget not specified
CritPtArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by Argonne and UIUC, with contributions from 60+ researchers globally. CritPt is under review by its authors following external feedback · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-08.	Not reported	10.57% Reported settings Mistral Large 4 Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-4; Mode from evaluator isReasoning metadata; effort budget not specified
GDP.pdf: All-pass RateArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of attempts where every atomic criterion passed · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-08.	Not reported	18.6% Reported settings Mistral Large 4 Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-4; Mode from evaluator isReasoning metadata; effort budget not specified
GDPval-AA v2.1 LeaderboardArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Elo rating for performance on real-world work tasks · Anchored to DeepSeek V4.1 Flash (max) at 1600 · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-10-08.	Not reported	1,423.91 Elo Reported settings Mistral Large 4 Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-4; Mode from evaluator isReasoning metadata; effort budget not specified
Humanity's Last ExamArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-08.	Not reported	35.03% Reported settings Mistral Large 4 Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-4; Mode from evaluator isReasoning metadata; effort budget not specified
MMMU-ProArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-08.	Not reported	76.42% Reported settings Mistral Large 4 Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-4; Mode from evaluator isReasoning metadata; effort budget not specified
AA-Omniscience IndexArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct. · Evaluation results measured independently by Artificial Analysis Unit: index. Source collected 2026-10-08.	Not reported	-5.3 Reported settings Mistral Large 4 Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-4; Mode from evaluator isReasoning metadata; effort budget not specified
AA-Omniscience AccuracyArtificial Analysis · 6000 questions; 1 attempt; correct-answer share; GPT-5.6 Luna medium grader Benchmark details AA-Omniscience Accuracy (higher is better) measures the proportion of correctly answered questions out of all questions, regardless of whether the model chooses to answer · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-08.	Not reported	25.82% Reported settings Mistral Large 4 Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-4; Mode from evaluator isReasoning metadata; effort budget not specified
SciCodeArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark curated by scientists across 16 disciplines. SciCode is under review following an independent audit of the dataset · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-08.	Not reported	54.17% Reported settings Mistral Large 4 Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-4; Mode from evaluator isReasoning metadata; effort budget not specified
Terminal-Bench v4.0Artificial Analysis · mini-SWE-agent v2.4.6; 66 tasks; pass@1 averaged over 3 repeats; 500 steps; task timeout up to 8 hours Benchmark details Benchmark developed by the Laude Institute, Stanford, and open-source contributors · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-08.	Not reported	26.77% Reported settings Mistral Large 4 Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-4; Mode from evaluator isReasoning metadata; effort budget not specified
LiveBench · AMPS Hard · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-08.	98% Reported settings LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; mistral-large-4-high; checkpoint=mistral-large-4 LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label. Source label needs review	Not reported
LiveBench · code completion · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-08.	78.26% Reported settings LiveBench official task evaluation; livebench-2026-06-25-code_completion; mistral-large-4-high; checkpoint=mistral-large-4 LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label. Source label needs review	Not reported
LiveBench · code generation · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-08.	76.06% Reported settings LiveBench official task evaluation; livebench-2026-06-25-code_generation; mistral-large-4-high; checkpoint=mistral-large-4 LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label. Source label needs review	Not reported
LiveBench · connections · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-08.	48% Reported settings LiveBench official task evaluation; livebench-2026-06-25-connections; mistral-large-4-high; checkpoint=mistral-large-4 LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label. Source label needs review	Not reported
LiveBench · consecutive events · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-08.	80.53% Reported settings LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; mistral-large-4-high; checkpoint=mistral-large-4 LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label. Source label needs review	Not reported
LiveBench · integrals with game · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-08.	90% Reported settings LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; mistral-large-4-high; checkpoint=mistral-large-4 LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label. Source label needs review	Not reported
LiveBench · javascript · 2026-06-25LiveBench · LiveBench Mini-SWE-Agent, 250-step limit Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-08.	68.18% Reported settings LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; mistral-large-4-high; checkpoint=mistral-large-4 LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label. Source label needs review	Not reported
LiveBench · logic with navigation · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-08.	68% Reported settings LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; mistral-large-4-high; checkpoint=mistral-large-4 LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label. Source label needs review	Not reported
LiveBench · math comp · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-08.	97.06% Reported settings LiveBench official task evaluation; livebench-2026-06-25-math_comp; mistral-large-4-high; checkpoint=mistral-large-4 LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label. Source label needs review	Not reported
LiveBench · olympiad · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-08.	89.28% Reported settings LiveBench official task evaluation; livebench-2026-06-25-olympiad; mistral-large-4-high; checkpoint=mistral-large-4 LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label. Source label needs review	Not reported
LiveBench · paraphrase · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-08.	63.97% Reported settings LiveBench official task evaluation; livebench-2026-06-25-paraphrase; mistral-large-4-high; checkpoint=mistral-large-4 LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label. Source label needs review	Not reported
LiveBench · plot unscrambling · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-08.	40.93% Reported settings LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; mistral-large-4-high; checkpoint=mistral-large-4 LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label. Source label needs review	Not reported
LiveBench · python · 2026-06-25LiveBench · LiveBench Mini-SWE-Agent, 250-step limit Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-08.	60% Reported settings LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; mistral-large-4-high; checkpoint=mistral-large-4 LiveBench reports High, but the official Mistral Large 4 model card does not establish a named High API effort setting. This is an evaluator configuration label. Source label needs review	Not reported

What these comparisons mean

Each source reports its own effort labels. Matching labels do not establish equal compute budgets or identical fallback behavior. Open Reported settings to inspect the exact model name, agent and task coverage. Multiple results at one level remain visible rather than selecting the best. Source-reported None or Non-reasoning labels are not treated as evidence that an API supports those settings.

These measurements use their own dated source collection. The leaderboard fits identified configurations jointly; it contains no pooled model ratings. Explicit thinking budgets are separate configurations. Read the methodology.

Download all effort benchmark results · 8,798 results across 256 models · Collected 2026-10-08

Mistral Large 4

Compare with

One configuration, seven capabilities

Agentic

Hard reasoning

Coding

Human pref

Knowledge

Multimodal

Long context

Capability score evidence

Benchmark results