RankingMistral Medium 3.5

Mistral Medium 3.5

Data updated 12 Sept 2026

13 published benchmark measures · 6 benchmark families contribute across 4 task areas. 4 capability estimates available in the full profile. See all results ↓ · Compare published benchmarks →

Model evidence summary

Choose a configuration

A model-wide score would mix effort settings. This page summarizes published evidence; only identified configurations receive leaderboard ranks.

Compare measured configurations →

The capability chart summarizes evidence across reported settings, not a runnable configuration or a leaderboard rank.

Performance profile

Capabilities

Adjusted comparison score · 0–100

Filled points are supported; hollow points are preliminary. Lines stop at unknown capabilities. Exact values and sources follow below.

Agentic2 families · 1 with independent evidence · Supported1.4

2 core families; 44 direct opponents across 19 labs.

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: 0.8–1.9; 2/11 scenarios unsupported. Without one publisher: 0.7–24.4; 2/15 unsupported. Smoothing check: 0.3–6.7; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage; source sensitivity still requires inspection. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

GDPval: 50.0 observed win share
artificialanalysis.ai · Source 1
Browsecomp: 25.0 observed win share
Mistral · Source 1

Hard reasoning2 families · 1 with independent evidence · Supported5.2

2 core families; 26 direct opponents across 11 labs.

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: 3.8–7.7; 2/7 scenarios unsupported. Without one publisher: 3.3–7.7; 2/16 unsupported. Smoothing check: 1.4–15.8; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

GPQA: 0.0 observed win share
artificialanalysis.ai · Source 1
Aime: 25.0 observed win share
Mistral · Source 1

Coding1 families · 0 with independent evidence · Preliminary3.2

1 core families; 4 direct opponents across 3 labs. Needs broader benchmark and opponent support

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 7/7 scenarios unsupported. Without one publisher: No supported estimate; 20/20 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

SWE-bench Verified: 50.0 observed win share
Mistral · Source 1

Human pref1 families · 1 with independent evidence · Supported16.3

1 core families; 114 direct opponents across 19 labs.

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 1/1 scenarios unsupported. Without one publisher: No supported estimate; 1/1 unsupported. Smoothing check: 7.0–29.4; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: cross-family and cross-publisher predictions could not be evaluated from the available comparison network. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

Human preference (Arena): 65.8 observed win share
lmarena.ai · Source 1

KnowledgeNo comparable evidenceUnknown

0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 4/4 scenarios unsupported. Without one publisher: No supported estimate; 5/5 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: almost no publisher-held-out comparisons remained estimable. Cross-source validity is unresolved. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

MultimodalNo comparable evidenceUnknown

0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 8/8 scenarios unsupported. Without one publisher: No supported estimate; 8/8 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: limited publisher-held-out coverage. Cross-source validity is unresolved. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

Long contextNo comparable evidenceUnknown

0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 5/5 scenarios unsupported. Without one publisher: No supported estimate; 5/5 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts underperformed neutral predictions. Treat this as an exploratory estimate. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

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.

Compare 3 effort levels across 32 benchmark/harness combinations →

Reported effort · Maximum reasoning + unspecified

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.

Maximum reasoning: 10 observations
Not specified: 3 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 evidence

Compare capability profiles →

Score contributions and missing evidence

6 contributing families across 4 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: api-listed
Availability: Documented provider API; account and region restrictions may apply
Family: Mistral
Released: 2026-04-28
Context: 256,000 tokens
License: Modified MIT
Model card: https://docs.mistral.ai/models/mistral-medium-3-5-26-04
Default Capability family coverage: /badge/mistral-medium-3.5.svg

Benchmark scores & sources

Original results, evaluation harnesses, and evidence behind this model.

Benchmark	Bucket	Score	Harness	Evidence	Source-recorded date
AIME 2025 avg@16 · source release snapshot; version not specified	Hard reasoning	86.3% Reported settings & source Maximum reasoning; Sonnet4.6 external API truncation caveat. First-party reported result; comparator results retain the source evaluation setup. Mistral Medium 3.5 model card performance charts · images/image1.png · reviewed 2026-09-06	Published configuration Effort: Maximum reasoning contributes to capability	lab self-report	Reviewed 2026-09-06
AllenAI IFBench · source release snapshot; version not specified	Supporting evidence	69% Reported settings & source Maximum reasoning; Sonnet4.6 external API truncation caveat. First-party reported result; comparator results retain the source evaluation setup. Mistral Medium 3.5 model card performance charts · images/image1.png · reviewed 2026-09-06	Published configuration Effort: Maximum reasoning	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
BeyondAIME avg@16 · source release snapshot; version not specified	Supporting evidence	66.9% Reported settings & source Maximum reasoning; Sonnet4.6 external API truncation caveat. First-party reported result; comparator results retain the source evaluation setup. Mistral Medium 3.5 model card performance charts · images/image1.png · reviewed 2026-09-06	Published configuration Effort: Maximum reasoning	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
BrowseComp · source release snapshot; version not specified	Agentic	48.6% Reported settings & source Maximum reasoning; tau3 4 trials, GPT5.2 low simulator except Sierra reported comparisons; BrowseComp discard-all context at100k. First-party reported result; comparator results retain the source evaluation setup. Mistral Medium 3.5 model card performance charts · images/image4.png · reviewed 2026-09-06	Published configuration Effort: Maximum reasoning contributes to capability	lab self-report	Reviewed 2026-09-06
Collie · source release snapshot; version not specified	Supporting evidence	95.8% Reported settings & source Maximum reasoning; Sonnet4.6 external API truncation caveat. First-party reported result; comparator results retain the source evaluation setup. Mistral Medium 3.5 model card performance charts · images/image1.png · reviewed 2026-09-06	Published configuration Effort: Maximum reasoning	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
GDPval-AA	Agentic	875	Artificial Analysis GDPval-AA Effort: Not specified contributes to capability	official board	2026-09-12
GPQA Diamond	Hard reasoning	74.848%	GPQA Diamond reported Effort: Not specified contributes to capability	independent repro	2026-09-11
LMArena Text Arena	Human pref	1426	LMArena Text Effort: Not specified contributes to capability	official board	2026-09-11
SWE-bench Verified · source release snapshot; version not specified	Coding	77.6% Reported settings & source Maximum reasoning; tau3 4 trials, GPT5.2 low simulator except Sierra reported comparisons; BrowseComp discard-all context at100k. First-party reported result; comparator results retain the source evaluation setup. Mistral Medium 3.5 model card performance charts · images/image4.png · reviewed 2026-09-06	Published configuration Effort: Maximum reasoning contributes to capability	lab self-report	Reviewed 2026-09-06
tau3 Airline · source release snapshot; version not specified	Supporting evidence	72% Reported settings & source Maximum reasoning; tau3 4 trials, GPT5.2 low simulator except Sierra reported comparisons; BrowseComp discard-all context at100k. First-party reported result; comparator results retain the source evaluation setup. Mistral Medium 3.5 model card performance charts · images/image4.png · reviewed 2026-09-06	Published configuration Effort: Maximum reasoning	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
tau3 Banking · source release snapshot; version not specified	Supporting evidence	13.4% Reported settings & source Maximum reasoning; tau3 4 trials, GPT5.2 low simulator except Sierra reported comparisons; BrowseComp discard-all context at100k. First-party reported result; comparator results retain the source evaluation setup. Mistral Medium 3.5 model card performance charts · images/image4.png · reviewed 2026-09-06	Published configuration Effort: Maximum reasoning	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
tau3 Retail · source release snapshot; version not specified	Supporting evidence	76.1% Reported settings & source Maximum reasoning; tau3 4 trials, GPT5.2 low simulator except Sierra reported comparisons; BrowseComp discard-all context at100k. First-party reported result; comparator results retain the source evaluation setup. Mistral Medium 3.5 model card performance charts · images/image4.png · reviewed 2026-09-06	Published configuration Effort: Maximum reasoning	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
tau3 Telecom · source release snapshot; version not specified	Supporting evidence	91.4% Reported settings & source Maximum reasoning; tau3 4 trials, GPT5.2 low simulator except Sierra reported comparisons; BrowseComp discard-all context at100k. First-party reported result; comparator results retain the source evaluation setup. Mistral Medium 3.5 model card performance charts · images/image4.png · reviewed 2026-09-06	Published configuration Effort: Maximum reasoning	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
ARC-AGI-2	Hard reasoning	—	—	—	—
DeepSWE v1.1	Agentic	—	—	—	—
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	—	—	—	—