Benchmarks · /benchmarks/bridgebench-hallucination

Hallucination

Name: Hallucination
Creator: BridgeBench

BridgeBench hallucination benchmark for resisting fabricated answers.

Source · BridgeBench
Version · bridgebench snapshot 2026-05-15
Scores · 35

Test details

Verified but agingThis is a rubric-judged signal, so it is more structured than arena taste but still depends on the scoring rubric.

source

BridgeBench

metric

Score (%)

judge

Rubric

direction

higher better

group id

bridgebench_hallucination_2026_05

domain

Professional reasoning

What it measures vs what it misses

✓ Measures

Accuracy and fabrication resistance under prompts that invite unsupported claims.

✗ Misses

Coding execution quality. Tool-backed factuality.

Why this countsAccuracy and fabrication resistance under prompts that invite unsupported claims.Same-test ruleThis percentile only compares models inside the exact benchmark/version group shown here. It is not a universal score.What it missesCoding execution quality.

Leaderboard · this benchmark version

#1 · Grok 4.3

BB · May 1, 2026

Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 100%
Last updated: stale
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

79.8%

#2 · Gemini 3.1 Pro Preview

BB · May 1, 2026

Source label: google/gemini-3.1-pro-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 97.1%
Last updated: stale
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

79.1%

#3 · qwen3.6-plus

BB · May 1, 2026

Source label: openrouter/qwen/qwen3.6-plus

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 97.1%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

79.1%

#4 · kimi-k2.6

BB · May 1, 2026

Source label: openrouter/moonshotai/kimi-k2.6

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 91.2%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

78.3%

#5 · Qwen3.5 Plus

BB · May 1, 2026

Source label: openrouter/qwen/qwen3.5-plus-02-15

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 88.2%
Last updated: stale
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

77.3%

#6 · Claude Opus 4.7

BB · May 1, 2026

Source label: openrouter/anthropic/claude-opus-4.7

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 85.3%
Last updated: stale
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

77.1%

#7 · Claude Opus 4.5

BB · May 1, 2026

Source label: anthropic/claude-opus-4-5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 82.4%
Last updated: stale
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

76.9%

#8 · Claude Opus 4.6

BB · May 1, 2026

Source label: anthropic/claude-opus-4-6-apr14

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 82.4%
Last updated: stale
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

76.9%

#9 · Claude Sonnet 4.6

BB · May 1, 2026

Source label: anthropic/claude-sonnet-4-6

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 76.5%
Last updated: stale
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

76.6%

#10 · Grok 4.20

BB · May 1, 2026

Source label: x-ai/grok-4.20

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 73.5%
Last updated: stale
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

76.1%

#11 · Gemini 3 Pro Preview

BB · May 1, 2026

Source label: google/gemini-3-pro-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 70.6%
Last updated: stale
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

75.9%

#12 · Qwen3.6 Max Preview

BB · May 1, 2026

Source label: openrouter/qwen/qwen3.6-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 67.6%
Last updated: stale
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

75.8%

#13 · GPT-5.5

BB · May 1, 2026

Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 64.7%
Last updated: stale
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

73.6%

#14 · Claude Haiku 4.5

BB · May 1, 2026

Source label: anthropic/claude-haiku-4-5

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 61.8%
Last updated: stale
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

73%

#15 · GPT-5.4

BB · May 1, 2026

Source label: openai/gpt-5.4

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 58.8%
Last updated: stale
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

72.8%

#16 · glm-5.1

BB · May 1, 2026

Source label: z-ai/glm-5.1

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 55.9%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

72.7%

#17 · GPT-5.4 mini

BB · May 1, 2026

Source label: openai/gpt-5.4-mini

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 52.9%
Last updated: stale
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

71.9%

#18 · glm-5v-turbo

BB · May 1, 2026

Source label: openrouter/z-ai/glm-5v-turbo

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 50%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

71.4%

#19 · Grok 3 mini

BB · May 1, 2026

Source label: x-ai/grok-3-mini

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 50%
Last updated: stale
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

71.4%

#20 · gemma-4-31b-it

BB · May 1, 2026

Source label: google/gemma-4-31b-it

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 44.1%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

71.3%

#21 · Grok 4

BB · May 1, 2026

Source label: x-ai/grok-4

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 41.2%
Last updated: stale
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

71%

#22 · GLM 5 Turbo

BB · May 1, 2026

Source label: z-ai/glm-5-turbo

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 41.2%
Last updated: stale
Eligibility: Benchmark-derived GLM 5 Turbo is visible for receipts but excluded from default overall rankings.
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

71%

#23 · GPT-5.4 nano

BB · May 1, 2026

Source label: openai/gpt-5.4-nano

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 35.3%
Last updated: stale
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

69.6%

#24 · glm-5

BB · May 1, 2026

Source label: z-ai/glm-5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 32.4%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

68.6%

#25 · Kimi K2.5 (Reasoning)

BB · May 1, 2026

Source label: openrouter/moonshotai/kimi-k2.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 29.4%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

67.2%

#26 · GPT-4.1

BB · May 1, 2026

Source label: openai/gpt-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 29.4%
Last updated: stale
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

67.2%

#27 · mimo-v2.5

BB · May 1, 2026

Source label: openrouter/xiaomi/mimo-v2.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 23.5%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

66.9%

#28 · Grok 3

BB · May 1, 2026

Source label: x-ai/grok-3

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 23.5%
Last updated: stale
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

66.9%

#29 · minimax-m2.7

BB · May 1, 2026

Source label: minimax/MiniMax-M2.7

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 17.6%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

66.8%

#30 · mimo-v2.5-pro

BB · May 1, 2026

Source label: openrouter/xiaomi/mimo-v2.5-pro

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 14.7%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

65.8%

#31 · GPT-4o

BB · May 1, 2026

Source label: openai/gpt-4o

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 11.8%
Last updated: stale
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

65.5%

#32 · GPT-4o mini

BB · May 1, 2026

Source label: openai/gpt-4o-mini

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 8.8%
Last updated: stale
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

61.3%

#33 · minimax-m2.5

BB · May 1, 2026

Source label: minimax/MiniMax-M2.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 5.9%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

59.4%

#34 · Nemotron 3 Nano Omni 30B A3B Reasoning

BB · May 1, 2026

Source label: openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 2.9%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

54.3%

#35 · deepseek-v4-pro

BB · May 1, 2026

Source label: openrouter/deepseek/deepseek-v4-pro

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

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

Parsed from the BridgeBench page for bridgebench-hallucination.

51.1%

Benchmarks · /benchmarks/bridgebench-hallucination

Hallucination

BridgeBench hallucination benchmark for resisting fabricated answers.

Source · BridgeBench
Version · bridgebench snapshot 2026-05-15
Scores · 35

Test details

Verified but agingThis is a rubric-judged signal, so it is more structured than arena taste but still depends on the scoring rubric.

source

BridgeBench

metric

Score (%)

judge

Rubric

direction

higher better

group id

bridgebench_hallucination_2026_05

domain

Professional reasoning

What it measures vs what it misses

✓ Measures

Accuracy and fabrication resistance under prompts that invite unsupported claims.

✗ Misses

Coding execution quality. Tool-backed factuality.

Leaderboard · this benchmark version

#1 · Grok 4.3

BB · May 1, 2026

Source label: openrouter/x-ai/grok-4.3

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 100%
Last updated: stale
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

79.8%

#2 · Gemini 3.1 Pro Preview

BB · May 1, 2026

Source label: google/gemini-3.1-pro-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 97.1%
Last updated: stale
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

79.1%

#3 · qwen3.6-plus

BB · May 1, 2026

Source label: openrouter/qwen/qwen3.6-plus

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 97.1%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

79.1%

#4 · kimi-k2.6

BB · May 1, 2026

Source label: openrouter/moonshotai/kimi-k2.6

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 91.2%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

78.3%

#5 · Qwen3.5 Plus

BB · May 1, 2026

Source label: openrouter/qwen/qwen3.5-plus-02-15

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 88.2%
Last updated: stale
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

77.3%

#6 · Claude Opus 4.7

BB · May 1, 2026

Source label: openrouter/anthropic/claude-opus-4.7

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 85.3%
Last updated: stale
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

77.1%

#7 · Claude Opus 4.5

BB · May 1, 2026

Source label: anthropic/claude-opus-4-5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 82.4%
Last updated: stale
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

76.9%

#8 · Claude Opus 4.6

BB · May 1, 2026

Source label: anthropic/claude-opus-4-6-apr14

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 82.4%
Last updated: stale
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

76.9%

#9 · Claude Sonnet 4.6

BB · May 1, 2026

Source label: anthropic/claude-sonnet-4-6

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 76.5%
Last updated: stale
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

76.6%

#10 · Grok 4.20

BB · May 1, 2026

Source label: x-ai/grok-4.20

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 73.5%
Last updated: stale
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

76.1%

#11 · Gemini 3 Pro Preview

BB · May 1, 2026

Source label: google/gemini-3-pro-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 70.6%
Last updated: stale
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

75.9%

#12 · Qwen3.6 Max Preview

BB · May 1, 2026

Source label: openrouter/qwen/qwen3.6-max-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 67.6%
Last updated: stale
Eligibility: preview_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

75.8%

#13 · GPT-5.5

BB · May 1, 2026

Source label: openai/gpt-5.5

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 64.7%
Last updated: stale
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

73.6%

#14 · Claude Haiku 4.5

BB · May 1, 2026

Source label: anthropic/claude-haiku-4-5

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 61.8%
Last updated: stale
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

73%

#15 · GPT-5.4

BB · May 1, 2026

Source label: openai/gpt-5.4

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 58.8%
Last updated: stale
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

72.8%

#16 · glm-5.1

BB · May 1, 2026

Source label: z-ai/glm-5.1

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 55.9%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

72.7%

#17 · GPT-5.4 mini

BB · May 1, 2026

Source label: openai/gpt-5.4-mini

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 52.9%
Last updated: stale
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

71.9%

#18 · glm-5v-turbo

BB · May 1, 2026

Source label: openrouter/z-ai/glm-5v-turbo

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 50%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

71.4%

#19 · Grok 3 mini

BB · May 1, 2026

Source label: x-ai/grok-3-mini

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 50%
Last updated: stale
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

71.4%

#20 · gemma-4-31b-it

BB · May 1, 2026

Source label: google/gemma-4-31b-it

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 44.1%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

71.3%

#21 · Grok 4

BB · May 1, 2026

Source label: x-ai/grok-4

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 41.2%
Last updated: stale
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

71%

#22 · GLM 5 Turbo

BB · May 1, 2026

Source label: z-ai/glm-5-turbo

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 41.2%
Last updated: stale
Eligibility: Benchmark-derived GLM 5 Turbo is visible for receipts but excluded from default overall rankings.
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

71%

#23 · GPT-5.4 nano

BB · May 1, 2026

Source label: openai/gpt-5.4-nano

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 35.3%
Last updated: stale
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

69.6%

#24 · glm-5

BB · May 1, 2026

Source label: z-ai/glm-5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 32.4%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

68.6%

#25 · Kimi K2.5 (Reasoning)

BB · May 1, 2026

Source label: openrouter/moonshotai/kimi-k2.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 29.4%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

67.2%

#26 · GPT-4.1

BB · May 1, 2026

Source label: openai/gpt-4.1

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 29.4%
Last updated: stale
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

67.2%

#27 · mimo-v2.5

BB · May 1, 2026

Source label: openrouter/xiaomi/mimo-v2.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 23.5%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

66.9%

#28 · Grok 3

BB · May 1, 2026

Source label: x-ai/grok-3

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 23.5%
Last updated: stale
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

66.9%

#29 · minimax-m2.7

BB · May 1, 2026

Source label: minimax/MiniMax-M2.7

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 17.6%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

66.8%

#30 · mimo-v2.5-pro

BB · May 1, 2026

Source label: openrouter/xiaomi/mimo-v2.5-pro

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 14.7%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

65.8%

#31 · GPT-4o

BB · May 1, 2026

Source label: openai/gpt-4o

verified runtimeexact alias

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 11.8%
Last updated: stale
Eligibility: headline eligible
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

65.5%

#32 · GPT-4o mini

BB · May 1, 2026

Source label: openai/gpt-4o-mini

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 8.8%
Last updated: stale
Eligibility: historical_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

61.3%

#33 · minimax-m2.5

BB · May 1, 2026

Source label: minimax/MiniMax-M2.5

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 5.9%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

59.4%

#34 · Nemotron 3 Nano Omni 30B A3B Reasoning

BB · May 1, 2026

Source label: openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

Source URL: https://www.bridgebench.ai/hallucination
Percentile: 2.9%
Last updated: stale
Eligibility: benchmark_derived_model
Identity: provider alias (0.92)

Parsed from the BridgeBench page for bridgebench-hallucination.

54.3%

#35 · deepseek-v4-pro

BB · May 1, 2026

Source label: openrouter/deepseek/deepseek-v4-pro

verified runtimeexact aliasBackground only

Raw row drilldownsource, percentile, eligibility

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

Parsed from the BridgeBench page for bridgebench-hallucination.

51.1%

Hallucination

Test details

What it measures vs what it misses

✓ Measures

✗ Misses

Leaderboard · this benchmark version

Loading benchmark evidence.

Hallucination

Test details

What it measures vs what it misses

✓ Measures

✗ Misses

Leaderboard · this benchmark version