Search operators

brand: benchmark: record: model: metric: date: org:

Separate values with commas, or alternatives with uppercase OR. Example: brand:Meta, Anthropic benchmark:GPQA

IFBench

Benchmark Family
IFBench
Organization
Allen Institute for AI
Status
ACTIVE

Versions / Variants

Version or VariantReferenceStatusRecords
Unspecifiedifbench/defaultACTIVE358

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-00141-010 GPT-4.1 IFBench Overall 43% Unknown Primary source OPNAI-41
BR-0015-012 GPT-5 IFBench Overall 73.1% Unknown Primary source OPNAI-5
BR-0015-025 GPT-5 IFBench Overall 70.6% Unknown Primary source OPNAI-5
BR-0015-037 GPT-5 IFBench Overall 66.6% Unknown Primary source OPNAI-5
BR-0015-049 GPT-5 IFBench Overall 45.6% Unknown Primary source OPNAI-5
BR-00151-012 GPT-5.1 IFBench Overall 72.9% Unknown Primary source OPNAI-51
BR-00151-025 GPT-5.1 IFBench Overall 43.2% Unknown Primary source OPNAI-51
BR-00152-010 GPT-5.2 IFBench Overall 75.4% Unknown Primary source OPNAI-52
BR-00152-022 GPT-5.2 IFBench Overall 47.4% Unknown Primary source OPNAI-52
BR-00152-034 GPT-5.2 IFBench Overall 65.2% Unknown Primary source OPNAI-52
BR-00154-011 GPT-5.4 IFBench Overall 48.4% Unknown Primary source OPNAI-54
BR-00154-023 GPT-5.4 IFBench Overall 65.9% Unknown Primary source OPNAI-54
BR-00154-037 GPT-5.4 IFBench Overall 73.9% Unknown Primary source OPNAI-54
BR-00155-023 GPT-5.5 IFBench Overall 75.9% Unknown Primary source OPNAI-55
BR-00155-038 GPT-5.5 IFBench Overall 71% Unknown Primary source OPNAI-55
BR-00155-051 GPT-5.5 IFBench Overall 46.1% Unknown Primary source OPNAI-55
BR-00155-064 GPT-5.5 IFBench Overall 71.6% Unknown Primary source OPNAI-55
BR-00155-077 GPT-5.5 IFBench Overall 64.4% Unknown Primary source OPNAI-55
BR-00156SL-013 GPT-5.6 Sol IFBench Overall 66.5% Unknown Primary source OPNAI-56SL
BR-00156SL-027 GPT-5.6 Sol IFBench Overall 69.6% Unknown Primary source OPNAI-56SL
BR-00156SL-052 GPT-5.6 Sol IFBench Overall 69.2% Unknown Primary source OPNAI-56SL
BR-00156SL-066 GPT-5.6 Sol IFBench Overall 72.7% Unknown Primary source OPNAI-56SL
BR-00156SL-081 GPT-5.6 Sol IFBench Overall 71% Unknown Primary source OPNAI-56SL
BR-00156TR-012 GPT-5.6 Terra IFBench Overall 62.2% Unknown Primary source OPNAI-56TR
BR-00156TR-026 GPT-5.6 Terra IFBench Overall 64.4% Unknown Primary source OPNAI-56TR
BR-00156TR-051 GPT-5.6 Terra IFBench Overall 66.3% Unknown Primary source OPNAI-56TR
BR-00156TR-065 GPT-5.6 Terra IFBench Overall 71.2% Unknown Primary source OPNAI-56TR
BR-00156TR-080 GPT-5.6 Terra IFBench Overall 59.7% Unknown Primary source OPNAI-56TR
BR-002FB5-013 Claude Fable 5 IFBench Overall 63.5% Unknown Primary source ANTHR-FB5
BR-002H3-010 Claude 3 Haiku IFBench Overall 36.1% Unknown Primary source ANTHR-H3
BR-002H35-012 Claude 3.5 Haiku IFBench Overall 42.8% Unknown Primary source ANTHR-H35
BR-002H45-012 Claude 4.5 Haiku IFBench Overall 54.3% Unknown Primary source ANTHR-H45
BR-002H45-026 Claude 4.5 Haiku IFBench Overall 42% Unknown Primary source ANTHR-H45
BR-002O4-005 Claude 4 Opus IFBench Overall 43.3% Unknown Primary source ANTHR-O4
BR-002O4-013 Claude 4 Opus IFBench Overall 53.7% Unknown Primary source ANTHR-O4
BR-002O41-008 Claude 4.1 Opus IFBench Overall 55.4% Unknown Primary source ANTHR-O41
BR-002O45-010 Claude Opus 4.5 IFBench Overall 58% Unknown Primary source ANTHR-O45
BR-002O45-022 Claude Opus 4.5 IFBench Overall 43% Unknown Primary source ANTHR-O45
BR-002O46-010 Claude Opus 4.6 IFBench Overall 44.6% Unknown Primary source ANTHR-O46
BR-002O46-022 Claude Opus 4.6 IFBench Overall 53.1% Unknown Primary source ANTHR-O46
BR-002O47-018 Claude Opus 4.7 IFBench Overall 43.6% Unknown Primary source ANTHR-O47
BR-002O47-029 Claude Opus 4.7 IFBench Overall 58.6% Unknown Primary source ANTHR-O47
BR-002O48-031 Claude Opus 4.8 IFBench Overall 62.2% Unknown Primary source ANTHR-O48
BR-002S37-010 Claude 3.7 Sonnet IFBench Overall 48.3% Unknown Primary source ANTHR-S37
BR-002S37-021 Claude 3.7 Sonnet IFBench Overall 44% Unknown Primary source ANTHR-S37
BR-002S4-012 Claude 4 Sonnet IFBench Overall 54.7% Unknown Primary source ANTHR-S4
BR-002S4-025 Claude 4 Sonnet IFBench Overall 45.4% Unknown Primary source ANTHR-S4
BR-002S45-012 Claude 4.5 Sonnet IFBench Overall 57.3% Unknown Primary source ANTHR-S45
BR-002S45-025 Claude 4.5 Sonnet IFBench Overall 42.7% Unknown Primary source ANTHR-S45
BR-002S46-011 Claude Sonnet 4.6 IFBench Overall 41.2% Unknown Primary source ANTHR-S46
BR-002S46-025 Claude Sonnet 4.6 IFBench Overall 56.6% Unknown Primary source ANTHR-S46
BR-002S46-040 Claude Sonnet 4.6 IFBench Overall 42.4% Unknown Primary source ANTHR-S46
BR-00325F-010 Gemini 2.5 Flash IFBench Overall 50.3% Unknown Primary source GOOGL-G25F
BR-00325F-022 Gemini 2.5 Flash IFBench Overall 39% Unknown Primary source GOOGL-G25F
BR-00325P-012 Gemini 2.5 Pro IFBench Overall 48.7% Unknown Primary source GOOGL-G25P
BR-00335F-013 Gemini 3.5 Flash IFBench Overall 76.3% Unknown Primary source GOOGL-G35F
BR-00335F-026 Gemini 3.5 Flash IFBench Overall 47.3% Unknown Primary source GOOGL-G35F
BR-00335F-036 Gemini 3.5 Flash IFBench Overall 74.6% Unknown Primary source GOOGL-G35F
BR-0043-010 Grok 3 IFBench Overall 46.9% Unknown Primary source XAI-G3
BR-0044-010 Grok 4 IFBench Overall 53.7% Unknown Primary source XAI-G4
BR-00443-010 Grok 4.3 IFBench Overall 83.3% Unknown Primary source XAI-G43
BR-00443-024 Grok 4.3 IFBench Overall 47.6% Unknown Primary source XAI-G43
BR-00443-039 Grok 4.3 IFBench Overall 81.3% Unknown Primary source XAI-G43
BR-00443-054 Grok 4.3 IFBench Overall 81% Unknown Primary source XAI-G43
BR-00735-004 Qwen3.5-397B-A17B IFBench Overall 76.5 Unknown Primary source QWEN-35
BR-007QWEN25INSTRUCT72B-010 Qwen2.5 Instruct 72B IFBench Overall 36.9% Unknown Primary source QWEN-QWEN25INSTRUCT72B
BR-007QWEN306B-010 Qwen3 0.6B IFBench Overall 21.9% Unknown Primary source QWEN-QWEN306B
BR-007QWEN306B-021 Qwen3 0.6B IFBench Overall 23.3% Unknown Primary source QWEN-QWEN306B
BR-007QWEN314B-012 Qwen3 14B IFBench Overall 40.5% Unknown Primary source QWEN-QWEN314B
BR-007QWEN314B-024 Qwen3 14B IFBench Overall 23.9% Unknown Primary source QWEN-QWEN314B
BR-007QWEN317B-010 Qwen3 1.7B IFBench Overall 21.1% Unknown Primary source QWEN-QWEN317B
BR-007QWEN317B-021 Qwen3 1.7B IFBench Overall 26.9% Unknown Primary source QWEN-QWEN317B
BR-007QWEN3235BA22B-010 Qwen3 235B A22B IFBench Overall 36.6% Unknown Primary source QWEN-QWEN3235BA22B
BR-007QWEN3235BA22B-021 Qwen3 235B A22B IFBench Overall 38.7% Unknown Primary source QWEN-QWEN3235BA22B
BR-007QWEN3235BA22B2507-012 Qwen3 235B A22B 2507 IFBench Overall 51.2% Unknown Primary source QWEN-QWEN3235BA22B2507
BR-007QWEN3235BA22B2507INSTRUCT-010 Qwen3 235B A22B 2507 Instruct IFBench Overall 46.1% Unknown Primary source QWEN-QWEN3235BA22B2507INSTRUCT
BR-007QWEN330BA3B-010 Qwen3 30B A3B IFBench Overall 41.5% Unknown Primary source QWEN-QWEN330BA3B
BR-007QWEN330BA3B-021 Qwen3 30B A3B IFBench Overall 31.9% Unknown Primary source QWEN-QWEN330BA3B
BR-007QWEN330BA3B2507-012 Qwen3 30B A3B 2507 IFBench Overall 50.7% Unknown Primary source QWEN-QWEN330BA3B2507
BR-007QWEN330BA3B2507INSTRUCT-010 Qwen3 30B A3B 2507 Instruct IFBench Overall 33.1% Unknown Primary source QWEN-QWEN330BA3B2507INSTRUCT
BR-007QWEN332B-012 Qwen3 32B IFBench Overall 36.3% Unknown Primary source QWEN-QWEN332B
BR-007QWEN332B-019 Qwen3 32B IFBench Overall 31.5% Unknown Primary source QWEN-QWEN332B
BR-007QWEN34B-006 Qwen3 4B IFBench Overall 32.5% Unknown Primary source QWEN-QWEN34B
BR-007QWEN34B2507-010 Qwen3 4B 2507 IFBench Overall 49.8% Unknown Primary source QWEN-QWEN34B2507
BR-007QWEN34B2507INSTRUCT-010 Qwen3 4B 2507 Instruct IFBench Overall 33.5% Unknown Primary source QWEN-QWEN34B2507INSTRUCT
BR-007QWEN3508B-011 Qwen3.5 0.8B IFBench Overall 21.6% Unknown Primary source QWEN-QWEN3508B
BR-007QWEN3508B-026 Qwen3.5 0.8B IFBench Overall 21.5% Unknown Primary source QWEN-QWEN3508B
BR-007QWEN35122BA10B-012 Qwen3.5 122B A10B IFBench Overall 50.8% Unknown Primary source QWEN-QWEN35122BA10B
BR-007QWEN35122BA10B-027 Qwen3.5 122B A10B IFBench Overall 75.7% Unknown Primary source QWEN-QWEN35122BA10B
BR-007QWEN3527B-010 Qwen3.5 27B IFBench Overall 75.6% Unknown Primary source QWEN-QWEN3527B
BR-007QWEN3527B-023 Qwen3.5 27B IFBench Overall 46.9% Unknown Primary source QWEN-QWEN3527B
BR-007QWEN352B-012 Qwen3.5 2B IFBench Overall 29.1% Unknown Primary source QWEN-QWEN352B
BR-007QWEN352B-027 Qwen3.5 2B IFBench Overall 31.5% Unknown Primary source QWEN-QWEN352B
BR-007QWEN3535BA3B-010 Qwen3.5 35B A3B IFBench Overall 72.5% Unknown Primary source QWEN-QWEN3535BA3B
BR-007QWEN3535BA3B-023 Qwen3.5 35B A3B IFBench Overall 44.5% Unknown Primary source QWEN-QWEN3535BA3B
BR-007QWEN35397BA17B-012 Qwen3.5 397B A17B IFBench Overall 78.8% Unknown Primary source QWEN-QWEN35397BA17B
BR-007QWEN35397BA17B-027 Qwen3.5 397B A17B IFBench Overall 51.6% Unknown Primary source QWEN-QWEN35397BA17B
BR-007QWEN354B-012 Qwen3.5 4B IFBench Overall 33.3% Unknown Primary source QWEN-QWEN354B
BR-007QWEN354B-026 Qwen3.5 4B IFBench Overall 52% Unknown Primary source QWEN-QWEN354B
BR-007QWEN359B-012 Qwen3.5 9B IFBench Overall 37.8% Unknown Primary source QWEN-QWEN359B