Benchmarks · /benchmarks/provider-mmmu-pro

MMMU-Pro

Name: MMMU-Pro
Creator: Provider official evals

Provider-official MMMU-Pro results manually verified from public provider pages.

Source · Provider official evals
Version · 2026-Q2 public provider cards
Scores · 6

Test details

Visible tradeoffsThis is an objective signal, so it is mainly about measurable task performance rather than public taste.

source

Provider official evals

metric

Accuracy (%)

judge

Objective

direction

higher better

group id

provider_official_mmmu_pro_2026_q2

domain

Vision understanding

What it measures vs what it misses

✓ Measures

Multimodal understanding and reasoning across text-plus-visual tasks.

✗ Misses

Image generation/editing quality and non-benchmark UX.

Why this countsIt is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.Same-test ruleThis percentile only compares models inside the exact benchmark/version group shown here. It is not a universal score.What it missesIt does not tell you whether the model can generate or edit images well.

Leaderboard · this benchmark version

#1 · GPT-5.5

OFF · Apr 23, 2026

Official company resultmanual verifiedmanual verified

Raw row drilldownsource, percentile, eligibility

Source URL: https://openai.com/index/introducing-gpt-5-5/
Percentile: 100%
Last updated: recent
Eligibility: headline eligible
Identity: exact (1.00)

Verified against OpenAI's GPT-5.5 launch page dated April 23, 2026. Uses the published no-tools MMMU Pro figure. Checked 2026-04-29. Verification: manual_public_page_verification.

81.2%

#2 · GPT-5.4

OFF · Mar 5, 2026

Official company resultmanual verifiedmanual verified

Raw row drilldownsource, percentile, eligibility

Source URL: https://openai.com/index/introducing-gpt-5-4/
Percentile: 100%
Last updated: aging
Eligibility: headline eligible
Identity: exact (1.00)

Verified against OpenAI's GPT-5.4 launch page dated March 5, 2026. Uses the published no-tools MMMU Pro figure. Checked 2026-04-29. Verification: manual_public_page_verification.

81.2%

#3 · Gemini 3 Pro Preview

OFF · Apr 29, 2026

Official company resultmanual verifiedmanual verifiedBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://deepmind.google/models/gemini/pro/
Percentile: 60%
Last updated: recent
Eligibility: preview_model
Identity: exact (1.00)

Verified against the current Gemini Pro public model page. Page did not expose a visible page date on April 29, 2026. Uses the published MMMU-Pro figure for Gemini 3 Pro Preview. Checked 2026-04-29. Verification: manual_public_page_verification.

81%

#4 · Gemini 3.1 Pro

OFF · Apr 29, 2026

Official company resultmanual verifiedmanual verified

Raw row drilldownsource, percentile, eligibility

Source URL: https://deepmind.google/models/gemini/pro/
Percentile: 40%
Last updated: recent
Eligibility: headline eligible
Identity: exact (1.00)

Verified against the current Gemini Pro public model page. Page did not expose a visible page date on April 29, 2026. Uses the published MMMU-Pro figure for Gemini 3.1 Pro. Checked 2026-04-29. Verification: manual_public_page_verification.

80.5%

#5 · Claude Sonnet 4.6

OFF · Apr 29, 2026

Official company resultmanual verifiedmanual verified

Raw row drilldownsource, percentile, eligibility

Source URL: https://anthropic.com/claude-sonnet-4-6-system-card
Percentile: 20%
Last updated: recent
Eligibility: headline eligible
Identity: exact (1.00)

Verified against Anthropic's public Claude Sonnet 4.6 system card, checked on April 29, 2026. Uses the published no-tools MMMU-Pro figure. Checked 2026-04-29. Verification: manual_public_page_verification.

74.5%

#6 · Claude Opus 4.6

OFF · Apr 29, 2026

Official company resultmanual verifiedmanual verifiedBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://anthropic.com/claude-opus-4-6-system-card
Percentile: 0%
Last updated: recent
Eligibility: historical_model
Identity: exact (1.00)

Verified against Anthropic's public Claude Opus 4.6 system card, checked on April 29, 2026. Uses the published no-tools MMMU-Pro figure. Checked 2026-04-29. Verification: manual_public_page_verification.

73.9%

Benchmarks · /benchmarks/provider-mmmu-pro

MMMU-Pro

Provider-official MMMU-Pro results manually verified from public provider pages.

Source · Provider official evals
Version · 2026-Q2 public provider cards
Scores · 6

Test details

Visible tradeoffsThis is an objective signal, so it is mainly about measurable task performance rather than public taste.

source

Provider official evals

metric

Accuracy (%)

judge

Objective

direction

higher better

group id

provider_official_mmmu_pro_2026_q2

domain

Vision understanding

What it measures vs what it misses

✓ Measures

Multimodal understanding and reasoning across text-plus-visual tasks.

✗ Misses

Image generation/editing quality and non-benchmark UX.

Leaderboard · this benchmark version

#1 · GPT-5.5

OFF · Apr 23, 2026

Official company resultmanual verifiedmanual verified

Raw row drilldownsource, percentile, eligibility

Source URL: https://openai.com/index/introducing-gpt-5-5/
Percentile: 100%
Last updated: recent
Eligibility: headline eligible
Identity: exact (1.00)

Verified against OpenAI's GPT-5.5 launch page dated April 23, 2026. Uses the published no-tools MMMU Pro figure. Checked 2026-04-29. Verification: manual_public_page_verification.

81.2%

#2 · GPT-5.4

OFF · Mar 5, 2026

Official company resultmanual verifiedmanual verified

Raw row drilldownsource, percentile, eligibility

Source URL: https://openai.com/index/introducing-gpt-5-4/
Percentile: 100%
Last updated: aging
Eligibility: headline eligible
Identity: exact (1.00)

Verified against OpenAI's GPT-5.4 launch page dated March 5, 2026. Uses the published no-tools MMMU Pro figure. Checked 2026-04-29. Verification: manual_public_page_verification.

81.2%

#3 · Gemini 3 Pro Preview

OFF · Apr 29, 2026

Official company resultmanual verifiedmanual verifiedBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://deepmind.google/models/gemini/pro/
Percentile: 60%
Last updated: recent
Eligibility: preview_model
Identity: exact (1.00)

81%

#4 · Gemini 3.1 Pro

OFF · Apr 29, 2026

Official company resultmanual verifiedmanual verified

Raw row drilldownsource, percentile, eligibility

Source URL: https://deepmind.google/models/gemini/pro/
Percentile: 40%
Last updated: recent
Eligibility: headline eligible
Identity: exact (1.00)

80.5%

#5 · Claude Sonnet 4.6

OFF · Apr 29, 2026

Official company resultmanual verifiedmanual verified

Raw row drilldownsource, percentile, eligibility

Source URL: https://anthropic.com/claude-sonnet-4-6-system-card
Percentile: 20%
Last updated: recent
Eligibility: headline eligible
Identity: exact (1.00)

74.5%

#6 · Claude Opus 4.6

OFF · Apr 29, 2026

Official company resultmanual verifiedmanual verifiedBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://anthropic.com/claude-opus-4-6-system-card
Percentile: 0%
Last updated: recent
Eligibility: historical_model
Identity: exact (1.00)

73.9%

MMMU-Pro

Test details

What it measures vs what it misses

✓ Measures

✗ Misses

Leaderboard · this benchmark version

Loading benchmark evidence.

MMMU-Pro

Test details

What it measures vs what it misses

✓ Measures

✗ Misses

Leaderboard · this benchmark version