RankingEffort benchmarks

Magistral Medium 1.2 effort benchmarks

Compare measured Low, Medium, High and other settings. Every number keeps its source.

Model

Magistral Medium 1.2

17 measured results · 1 reported effort labels · 17 benchmark/harness combinations. Model evidence and sources →

Capability score evidence

Magistral Medium 1.2 · Reasoning: 6.2 overall comparison score. Meets the overall evidence requirements.

Which sources carry the weight?

Artificial Analysis · 100.0% direct comparison weight · independent

These shares describe the comparisons entering the fit, not fractions of the final score.

How sensitive is this score?

Remove one evaluator or family and refit the graph against the same overall panel. Values use the matching dataset audited 2026-09-12. These are sensitivity checks, not confidence intervals; ranking eligibility may also change.

Removed evidence	Recomputed score	Change
Artificial Analysis	Comparison path lost	—
ARC Prize	7.4	+1.2
Datacurve	5.3	-0.9
LiveCodeBench	6.1	-0.1
Scale	6.8	+0.7
Terminal-Bench	6.2	-0.0
Cognition	6.5	+0.3
LiveBench	6.3	+0.1
SWE-rebench	6.3	+0.2
Epoch AI	6.2	+0.0
Vals AI	6.0	-0.2
Provider reports · Anthropic	6.2	+0.0
Provider reports · Moonshot AI	6.2	-0.0
Provider reports · Meta	6.2	-0.0
Provider reports · Mistral	6.2	+0.0
All provider reports	6.2	-0.0

Every benchmark family

Removed evidence	Recomputed score	Change
arc-agi	7.3	+1.2
deepswe	5.3	-0.9
mmmu-pro	6.8	+0.7
omniscience	5.8	-0.4
gdpval	6.5	+0.4
hle	6.5	+0.3
epoch-game-puzzles	5.9	-0.3
livecodebench	5.9	-0.3
frontiercode	6.5	+0.3
simpleqa	6.4	+0.2
critpt	6.0	-0.2
aime	6.0	-0.2
terminal-bench	6.3	+0.2
swe-rebench	6.3	+0.2
mmlu-pro	6.3	+0.1
gpqa	6.1	-0.1
scicode	6.3	+0.1
multi-swe-bench	6.1	-0.1
livebench-instructions	6.3	+0.1
aa-lcr	6.1	-0.1
gmmlu	6.3	+0.1
harvey	6.1	-0.1
livebench-language	6.2	+0.1
gdp-pdf	6.2	+0.1
frontiermath	6.2	+0.1
apex-agents	6.2	+0.1
swe-atlas-qna	6.1	-0.1
livebench-coding	6.1	-0.0
arc-agi-3	6.1	-0.0
vibe-code	6.1	-0.0
livebench-reasoning	6.1	-0.0
vals-finance-agent	6.1	-0.0
briefcase	6.2	-0.0
vals-legal-research	6.2	-0.0
swe-atlas-test-writing	6.2	-0.0
vals-code-migration	6.2	-0.0
math500	6.2	+0.0
itbench	6.2	-0.0
automationbench	6.2	-0.0
analyst-agent	6.2	+0.0
livebench-data	6.2	+0.0
ifbench	6.2	-0.0
livebench-math	6.2	+0.0
vals-excel-modeling	6.2	-0.0
swe-atlas-refactoring	6.2	-0.0
enigma-eval	6.2	+0.0
enterprise-ops	6.2	-0.0
swe-bench-pro	6.2	+0.0
tau-bench	6.2	-0.0

What evidence is missing from the fit?

Across all collected settings for this model: 23 observations, 16 contributing, 1 matched without graph weight and 6 excluded. Counts do not establish rank eligibility.

1 · Benchmark family or source protocol has not been reviewed
4 · 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 →

Capability profile

One configuration, seven capabilities

Comparison score · 0–100

AMagistral Medium 1.2 · Reasoning4 of 7 capabilities supported

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

Agentic
A5.0Supported
Hard reasoning
A9.0Supported
Coding
A7.2Supported
Human pref
Unknown
Knowledge
A8.2Supported
Multimodal
A4.4Preliminary
Long context
A10.0Preliminary

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.

Compare this configuration →Explore the model evidence profile →

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	Reasoning
AIME 2025Artificial 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 2026-09-12.	82% Reported settings Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; 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 2026-09-12.	53% Reported settings Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; 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 · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	0.29% Reported settings Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified
GDPval-AA v2 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 a human baseline of 1,000 · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-09-12.	361.94 Elo Reported settings Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified
Global-MMLU-LiteArtificial 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 2026-09-12.	81.57% Reported settings Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified
GPQA DiamondArtificial 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 2026-09-12.	73.94% Reported settings Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; 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 2026-09-12.	10.29% Reported settings Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified
IFBenchArtificial 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 2026-09-12.	42.99% Reported settings Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified
LiveCodeBenchArtificial 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 2026-09-12.	75.03% Reported settings Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified
MMLU-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 2026-09-12.	81.51% Reported settings Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; 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 2026-09-12.	59.65% Reported settings Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; 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 2026-09-12.	-26.73 Reported settings Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; 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 2026-09-12.	20.78% Reported settings Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified
𝜏²-Bench TelecomArtificial 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 2026-09-12.	52.05% Reported settings Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified
𝜏³-BankingArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by Sierra Research · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	5.57% Reported settings Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified
Terminal-Bench HardArtificial 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 2026-09-12.	12.88% Reported settings Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified
Terminal-Bench v2.1Artificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by the Laude Institute and open-source contributors · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	12.36% Reported settings Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified

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 · 7,424 results across 240 models · Collected 2026-09-12

Magistral Medium 1.2 effort benchmarks