Benchmarks · /benchmarks/bridgebench-overall-quality

Overall quality

Name: Overall quality
Creator: BridgeBench

BridgeBench overall quality score across its coding-heavy benchmark mix.

Source · BridgeBench
Version · bridgebench snapshot 2026-05-15
Scores · 23

Test details

Verified but agingThis is a combined signal, so it bundles multiple inputs and should not be treated as one clean test.

source

BridgeBench

metric

Quality (%)

judge

Combined

direction

higher better

group id

bridgebench_overall_quality_2026_05

domain

Coding

What it measures vs what it misses

✓ Measures

Engineering quality across BridgeBench's tracked coding categories.

✗ Misses

Single-task drilldowns. Cost and latency details.

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 · qwen3.6-max-preview

BB · Undated

Source label: Qwen 3.6 Max Preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 100%
Last updated: archived
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

91.4%

#2 · Claude Opus 4.6

BB · Undated

Source label: Claude Opus 4.6

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 95.5%
Last updated: archived
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

91.1%

#3 · Grok 4.3

BB · Undated

Source label: Grok 4.3

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 90.9%
Last updated: archived
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

90.6%

#4 · Claude Opus 4.7

BB · Undated

Source label: Claude Opus 4.7

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 86.4%
Last updated: archived
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

89.7%

#5 · Claude Sonnet 4.6

BB · Undated

Source label: Claude Sonnet 4.6

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 81.8%
Last updated: archived
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

89.5%

#6 · Grok 4.20

BB · Undated

Source label: Grok 4.20 Reasoning

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 77.3%
Last updated: archived
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

88.3%

#7 · qwen3.6-plus

BB · Undated

Source label: Qwen 3.6 Plus

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 72.7%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

86.8%

#8 · GPT-5.4

BB · Undated

Source label: GPT-5.4

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 68.2%
Last updated: archived
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

86.3%

#9 · kimi-k2.6

BB · Undated

Source label: Kimi K2.6

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 63.6%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

85.3%

#10 · GPT-5.5

BB · Undated

Source label: GPT-5.5

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 59.1%
Last updated: archived
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

83.6%

#11 · GPT-5.4 mini

BB · Undated

Source label: GPT-5.4 Mini

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 54.5%
Last updated: archived
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

77.6%

#12 · Gemini 3.1 Pro

BB · Undated

Source label: Gemini 3.1 Pro

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 50%
Last updated: archived
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

76.2%

#13 · GPT-5.4 nano

BB · Undated

Source label: GPT-5.4 Nano

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 45.5%
Last updated: archived
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

70.9%

#14 · gemma-4-31b

BB · Undated

Source label: Gemma 4 31B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 40.9%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

68.2%

#15 · glm-5.1

BB · Undated

Source label: GLM 5.1

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 36.4%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

65.7%

#16 · mimo-v2.5-pro

BB · Undated

Source label: MiMo v2.5 Pro

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 31.8%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

65.2%

#17 · glm-5v-turbo

BB · Undated

Source label: GLM 5V Turbo

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 27.3%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

60.6%

#18 · mimo-v2.5

BB · Undated

Source label: MiMo V2.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 22.7%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

54.4%

#19 · minimax-m2.5

BB · Undated

Source label: MiniMax M2.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 18.2%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

51.1%

#20 · minimax-m2.7

BB · Undated

Source label: MiniMax M2.7

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 13.6%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

45.3%

#21 · Kimi K2.5 (Reasoning)

BB · Undated

Source label: Kimi K2.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 9.1%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

44.1%

#22 · deepseek-v4-pro

BB · Undated

Source label: DeepSeek V4 Pro

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 4.5%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

16.3%

#23 · Nemotron 3 Nano Omni 30B A3B Reasoning

BB · Undated

Source label: Nemotron 3 Nano Omni 30b A3b Reasoning:Free

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 0%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

12.3%

Benchmarks · /benchmarks/bridgebench-overall-quality

Overall quality

BridgeBench overall quality score across its coding-heavy benchmark mix.

Source · BridgeBench
Version · bridgebench snapshot 2026-05-15
Scores · 23

Test details

Verified but agingThis is a combined signal, so it bundles multiple inputs and should not be treated as one clean test.

source

BridgeBench

metric

Quality (%)

judge

Combined

direction

higher better

group id

bridgebench_overall_quality_2026_05

domain

Coding

What it measures vs what it misses

✓ Measures

Engineering quality across BridgeBench's tracked coding categories.

✗ Misses

Single-task drilldowns. Cost and latency details.

Leaderboard · this benchmark version

#1 · qwen3.6-max-preview

BB · Undated

Source label: Qwen 3.6 Max Preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 100%
Last updated: archived
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

91.4%

#2 · Claude Opus 4.6

BB · Undated

Source label: Claude Opus 4.6

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 95.5%
Last updated: archived
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

91.1%

#3 · Grok 4.3

BB · Undated

Source label: Grok 4.3

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 90.9%
Last updated: archived
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

90.6%

#4 · Claude Opus 4.7

BB · Undated

Source label: Claude Opus 4.7

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 86.4%
Last updated: archived
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

89.7%

#5 · Claude Sonnet 4.6

BB · Undated

Source label: Claude Sonnet 4.6

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 81.8%
Last updated: archived
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

89.5%

#6 · Grok 4.20

BB · Undated

Source label: Grok 4.20 Reasoning

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 77.3%
Last updated: archived
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

88.3%

#7 · qwen3.6-plus

BB · Undated

Source label: Qwen 3.6 Plus

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 72.7%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

86.8%

#8 · GPT-5.4

BB · Undated

Source label: GPT-5.4

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 68.2%
Last updated: archived
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

86.3%

#9 · kimi-k2.6

BB · Undated

Source label: Kimi K2.6

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 63.6%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

85.3%

#10 · GPT-5.5

BB · Undated

Source label: GPT-5.5

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 59.1%
Last updated: archived
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

83.6%

#11 · GPT-5.4 mini

BB · Undated

Source label: GPT-5.4 Mini

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 54.5%
Last updated: archived
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

77.6%

#12 · Gemini 3.1 Pro

BB · Undated

Source label: Gemini 3.1 Pro

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 50%
Last updated: archived
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

76.2%

#13 · GPT-5.4 nano

BB · Undated

Source label: GPT-5.4 Nano

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 45.5%
Last updated: archived
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

70.9%

#14 · gemma-4-31b

BB · Undated

Source label: Gemma 4 31B

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 40.9%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

68.2%

#15 · glm-5.1

BB · Undated

Source label: GLM 5.1

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 36.4%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

65.7%

#16 · mimo-v2.5-pro

BB · Undated

Source label: MiMo v2.5 Pro

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 31.8%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

65.2%

#17 · glm-5v-turbo

BB · Undated

Source label: GLM 5V Turbo

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 27.3%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

60.6%

#18 · mimo-v2.5

BB · Undated

Source label: MiMo V2.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 22.7%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

54.4%

#19 · minimax-m2.5

BB · Undated

Source label: MiniMax M2.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 18.2%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

51.1%

#20 · minimax-m2.7

BB · Undated

Source label: MiniMax M2.7

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 13.6%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

45.3%

#21 · Kimi K2.5 (Reasoning)

BB · Undated

Source label: Kimi K2.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 9.1%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

44.1%

#22 · deepseek-v4-pro

BB · Undated

Source label: DeepSeek V4 Pro

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 4.5%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

16.3%

#23 · Nemotron 3 Nano Omni 30B A3B Reasoning

BB · Undated

Source label: Nemotron 3 Nano Omni 30b A3b Reasoning:Free

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/overall
Percentile: 0%
Last updated: archived
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-overall-quality.

12.3%

Overall quality

Test details

What it measures vs what it misses

✓ Measures

✗ Misses

Leaderboard · this benchmark version

Loading benchmark evidence.

Overall quality

Test details

What it measures vs what it misses

✓ Measures

✗ Misses

Leaderboard · this benchmark version