Benchmarks · /benchmarks/provider-terminal-bench-2

Terminal-Bench 2.0

Name: Terminal-Bench 2.0
Creator: Provider official evals

Provider-official Terminal-Bench 2.0 results manually verified from public provider pages.

Source · Provider official evals
Version · 2026-Q2 public provider cards
Scores · 7

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_terminal_bench_2_2026_q2

domain

Coding

What it measures vs what it misses

✓ Measures

Multi-step terminal coding accuracy under agentic workflows.

✗ Misses

IDE ergonomics, code review style, and non-terminal coding work.

Why this countsIt tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.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 fully capture repo-scale iteration, IDE ergonomics, or long debugging loops.

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 Terminal-Bench 2.0 figure. Checked 2026-04-29. Verification: manual_public_page_verification.

82.7%

#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: 83.3%
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 Terminal-Bench 2.0 figure. Checked 2026-04-29. Verification: manual_public_page_verification.

75.1%

#3 · Claude Opus 4.7

OFF · Apr 29, 2026

Official company resultmanual verifiedmanual verified

Raw row drilldownsource, percentile, eligibility

Source URL: https://anthropic.com/claude-opus-4-7-system-card
Percentile: 66.7%
Last updated: recent
Eligibility: headline eligible
Identity: exact (1.00)

Verified against Anthropic's public Claude Opus 4.7 system card, checked on April 29, 2026. Uses the published Terminal-Bench 2.0 figure. Checked 2026-04-29. Verification: manual_public_page_verification.

69.4%

#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: 50%
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 Terminal-Bench 2.0 figure for Gemini 3.1 Pro. Checked 2026-04-29. Verification: manual_public_page_verification.

68.5%

#5 · 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: 33.3%
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 Terminal-Bench 2.0 figure. Checked 2026-04-29. Verification: manual_public_page_verification.

65.4%

#6 · 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: 16.7%
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 Terminal-Bench 2.0 figure. Checked 2026-04-29. Verification: manual_public_page_verification.

59.1%

#7 · 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: 0%
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 Terminal-Bench 2.0 figure for Gemini 3 Pro Preview. Checked 2026-04-29. Verification: manual_public_page_verification.

56.9%

Benchmarks · /benchmarks/provider-terminal-bench-2

Terminal-Bench 2.0

Provider-official Terminal-Bench 2.0 results manually verified from public provider pages.

Source · Provider official evals
Version · 2026-Q2 public provider cards
Scores · 7

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_terminal_bench_2_2026_q2

domain

Coding

What it measures vs what it misses

✓ Measures

Multi-step terminal coding accuracy under agentic workflows.

✗ Misses

IDE ergonomics, code review style, and non-terminal coding work.

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 Terminal-Bench 2.0 figure. Checked 2026-04-29. Verification: manual_public_page_verification.

82.7%

#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: 83.3%
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 Terminal-Bench 2.0 figure. Checked 2026-04-29. Verification: manual_public_page_verification.

75.1%

#3 · Claude Opus 4.7

OFF · Apr 29, 2026

Official company resultmanual verifiedmanual verified

Raw row drilldownsource, percentile, eligibility

Source URL: https://anthropic.com/claude-opus-4-7-system-card
Percentile: 66.7%
Last updated: recent
Eligibility: headline eligible
Identity: exact (1.00)

69.4%

#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: 50%
Last updated: recent
Eligibility: headline eligible
Identity: exact (1.00)

68.5%

#5 · 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: 33.3%
Last updated: recent
Eligibility: historical_model
Identity: exact (1.00)

65.4%

#6 · 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: 16.7%
Last updated: recent
Eligibility: headline eligible
Identity: exact (1.00)

59.1%

#7 · 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: 0%
Last updated: recent
Eligibility: preview_model
Identity: exact (1.00)

56.9%

Terminal-Bench 2.0

Test details

What it measures vs what it misses

✓ Measures

✗ Misses

Leaderboard · this benchmark version

Loading benchmark evidence.

Terminal-Bench 2.0

Test details

What it measures vs what it misses

✓ Measures

✗ Misses

Leaderboard · this benchmark version