tau2-bench

Benchmark Family
tau2-bench
Organization
Sierra
Status
ACTIVE

Versions / Variants

Version or VariantReferenceStatusRecords
Unspecifiedtau2-bench/defaultACTIVE350
Retailtau2-bench/retailACTIVE1
Telecomtau2-bench/telecomACTIVE2

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-00141-005 GPT-4.1 tau2-bench Overall 47.1% Unknown Primary source OPNAI-41
BR-0015-005 GPT-5 tau2-bench Overall 84.8% Unknown Primary source OPNAI-5
BR-0015-020 GPT-5 tau2-bench Overall 86.5% Unknown Primary source OPNAI-5
BR-0015-032 GPT-5 tau2-bench Overall 84.2% Unknown Primary source OPNAI-5
BR-0015-044 GPT-5 tau2-bench Overall 67% Unknown Primary source OPNAI-5
BR-00151-005 GPT-5.1 tau2-bench Overall 81.9% Unknown Primary source OPNAI-51
BR-00151-020 GPT-5.1 tau2-bench Overall 46.5% Unknown Primary source OPNAI-51
BR-00152-005 GPT-5.2 tau2-bench Overall 84.8% Unknown Primary source OPNAI-52
BR-00152-016 GPT-5.2 tau2-bench Overall 46.5% Unknown Primary source OPNAI-52
BR-00152-029 GPT-5.2 tau2-bench Overall 74.3% Unknown Primary source OPNAI-52
BR-00154-006 GPT-5.4 tau2-bench Overall 35.1% Unknown Primary source OPNAI-54
BR-00154-018 GPT-5.4 tau2-bench Overall 74.6% Unknown Primary source OPNAI-54
BR-00154-030 GPT-5.4 tau2-bench Overall 87.1% Unknown Primary source OPNAI-54
BR-00155-017 GPT-5.5 tau2-bench Overall 93.9% Unknown Primary source OPNAI-55
BR-00155-032 GPT-5.5 tau2-bench Overall 91.8% Unknown Primary source OPNAI-55
BR-00155-045 GPT-5.5 tau2-bench Overall 69.3% Unknown Primary source OPNAI-55
BR-00155-058 GPT-5.5 tau2-bench Overall 93% Unknown Primary source OPNAI-55
BR-00155-071 GPT-5.5 tau2-bench Overall 83.9% Unknown Primary source OPNAI-55
BR-00156SL-006 GPT-5.6 Sol tau2-bench Overall 76% Unknown Primary source OPNAI-56SL
BR-00156SL-020 GPT-5.6 Sol tau2-bench Overall 81% Unknown Primary source OPNAI-56SL
BR-00156SL-045 GPT-5.6 Sol tau2-bench Overall 83.3% Unknown Primary source OPNAI-56SL
BR-00156SL-059 GPT-5.6 Sol tau2-bench Overall 85.1% Unknown Primary source OPNAI-56SL
BR-00156SL-074 GPT-5.6 Sol tau2-bench Overall 84.8% Unknown Primary source OPNAI-56SL
BR-00156TR-006 GPT-5.6 Terra tau2-bench Overall 72.8% Unknown Primary source OPNAI-56TR
BR-00156TR-019 GPT-5.6 Terra tau2-bench Overall 78.4% Unknown Primary source OPNAI-56TR
BR-00156TR-044 GPT-5.6 Terra tau2-bench Overall 80.4% Unknown Primary source OPNAI-56TR
BR-00156TR-058 GPT-5.6 Terra tau2-bench Overall 86.3% Unknown Primary source OPNAI-56TR
BR-00156TR-073 GPT-5.6 Terra tau2-bench Overall 60.5% Unknown Primary source OPNAI-56TR
BR-002FB5-006 Claude Fable 5 tau2-bench Overall 98.5% Unknown Primary source ANTHR-FB5
BR-002H3-005 Claude 3 Haiku tau2-bench Overall 21.1% Unknown Primary source ANTHR-H3
BR-002H35-005 Claude 3.5 Haiku tau2-bench Overall 24.6% Unknown Primary source ANTHR-H35
BR-002H45-005 Claude 4.5 Haiku tau2-bench Overall 54.7% Unknown Primary source ANTHR-H45
BR-002H45-021 Claude 4.5 Haiku tau2-bench Overall 32.5% Unknown Primary source ANTHR-H45
BR-002O4-011 Claude 4 Opus tau2-bench Overall 73.4% Unknown Primary source ANTHR-O4
BR-002O41-005 Claude 4.1 Opus tau2-bench Overall 71.4% Unknown Primary source ANTHR-O41
BR-002O45-005 Claude Opus 4.5 tau2-bench Overall 89.5% Unknown Primary source ANTHR-O45
BR-002O45-017 Claude Opus 4.5 tau2-bench Overall 86.3% Unknown Primary source ANTHR-O45
BR-002O46-005 Claude Opus 4.6 tau2-bench Overall 84.8% Unknown Primary source ANTHR-O46
BR-002O46-017 Claude Opus 4.6 tau2-bench Overall 92.1% Unknown Primary source ANTHR-O46
BR-002O47-013 Claude Opus 4.7 tau2-bench Overall 74% Unknown Primary source ANTHR-O47
BR-002O47-023 Claude Opus 4.7 tau2-bench Overall 88.6% Unknown Primary source ANTHR-O47
BR-002O48-025 Claude Opus 4.8 tau2-bench Overall 94.4% Unknown Primary source ANTHR-O48
BR-002S37-005 Claude 3.7 Sonnet tau2-bench Overall 54.7% Unknown Primary source ANTHR-S37
BR-002S37-016 Claude 3.7 Sonnet tau2-bench Overall 50% Unknown Primary source ANTHR-S37
BR-002S4-005 Claude 4 Sonnet tau2-bench Overall 64.6% Unknown Primary source ANTHR-S4
BR-002S4-020 Claude 4 Sonnet tau2-bench Overall 52.3% Unknown Primary source ANTHR-S4
BR-002S45-005 Claude 4.5 Sonnet tau2-bench Overall 78.1% Unknown Primary source ANTHR-S45
BR-002S45-020 Claude 4.5 Sonnet tau2-bench Overall 70.5% Unknown Primary source ANTHR-S45
BR-002S46-006 Claude Sonnet 4.6 tau2-bench Overall 79.5% Unknown Primary source ANTHR-S46
BR-002S46-018 Claude Sonnet 4.6 tau2-bench Overall 75.7% Unknown Primary source ANTHR-S46
BR-002S46-035 Claude Sonnet 4.6 tau2-bench Overall 78.9% Unknown Primary source ANTHR-S46
BR-00325F-005 Gemini 2.5 Flash tau2-bench Overall 31.6% Unknown Primary source GOOGL-G25F
BR-00325F-017 Gemini 2.5 Flash tau2-bench Overall 14.9% Unknown Primary source GOOGL-G25F
BR-00325P-005 Gemini 2.5 Pro tau2-bench Overall 54.1% Unknown Primary source GOOGL-G25P
BR-00331P-012 Gemini 3.1 Pro tau2-bench Retail Overall 90.8% Unknown Primary source GOOGL-G31P
BR-00331P-013 Gemini 3.1 Pro tau2-bench Telecom Overall 99.3% Unknown Primary source GOOGL-G31P
BR-00335F-007 Gemini 3.5 Flash tau2-bench Overall 95.3% Unknown Primary source GOOGL-G35F
BR-00335F-022 Gemini 3.5 Flash tau2-bench Overall 58.8% Unknown Primary source GOOGL-G35F
BR-00335F-032 Gemini 3.5 Flash tau2-bench Overall 95.6% Unknown Primary source GOOGL-G35F
BR-0043-005 Grok 3 tau2-bench Overall 48.8% Unknown Primary source XAI-G3
BR-0044-005 Grok 4 tau2-bench Overall 74.9% Unknown Primary source XAI-G4
BR-00443-005 Grok 4.3 tau2-bench Overall 91.2% Unknown Primary source XAI-G43
BR-00443-017 Grok 4.3 tau2-bench Overall 65.8% Unknown Primary source XAI-G43
BR-00443-032 Grok 4.3 tau2-bench Overall 97.7% Unknown Primary source XAI-G43
BR-00443-049 Grok 4.3 tau2-bench Overall 88.9% Unknown Primary source XAI-G43
BR-00735-016 Qwen3.5-397B-A17B tau2-bench Overall 86.7 Unknown Primary source QWEN-35
BR-007QWEN25INSTRUCT72B-005 Qwen2.5 Instruct 72B tau2-bench Overall 34.5% Unknown Primary source QWEN-QWEN25INSTRUCT72B
BR-007QWEN306B-005 Qwen3 0.6B tau2-bench Overall 14.6% Unknown Primary source QWEN-QWEN306B
BR-007QWEN306B-016 Qwen3 0.6B tau2-bench Overall 21.1% Unknown Primary source QWEN-QWEN306B
BR-007QWEN314B-005 Qwen3 14B tau2-bench Overall 34.5% Unknown Primary source QWEN-QWEN314B
BR-007QWEN314B-019 Qwen3 14B tau2-bench Overall 32.2% Unknown Primary source QWEN-QWEN314B
BR-007QWEN317B-005 Qwen3 1.7B tau2-bench Overall 21.6% Unknown Primary source QWEN-QWEN317B
BR-007QWEN317B-016 Qwen3 1.7B tau2-bench Overall 26% Unknown Primary source QWEN-QWEN317B
BR-007QWEN3235BA22B-005 Qwen3 235B A22B tau2-bench Overall 27.2% Unknown Primary source QWEN-QWEN3235BA22B
BR-007QWEN3235BA22B-016 Qwen3 235B A22B tau2-bench Overall 24% Unknown Primary source QWEN-QWEN3235BA22B
BR-007QWEN3235BA22B2507-005 Qwen3 235B A22B 2507 tau2-bench Overall 53.2% Unknown Primary source QWEN-QWEN3235BA22B2507
BR-007QWEN3235BA22B2507INSTRUCT-005 Qwen3 235B A22B 2507 Instruct tau2-bench Overall 33.3% Unknown Primary source QWEN-QWEN3235BA22B2507INSTRUCT
BR-007QWEN330BA3B-005 Qwen3 30B A3B tau2-bench Overall 26% Unknown Primary source QWEN-QWEN330BA3B
BR-007QWEN330BA3B-016 Qwen3 30B A3B tau2-bench Overall 22.2% Unknown Primary source QWEN-QWEN330BA3B
BR-007QWEN330BA3B2507-005 Qwen3 30B A3B 2507 tau2-bench Overall 28.1% Unknown Primary source QWEN-QWEN330BA3B2507
BR-007QWEN330BA3B2507INSTRUCT-005 Qwen3 30B A3B 2507 Instruct tau2-bench Overall 10.2% Unknown Primary source QWEN-QWEN330BA3B2507INSTRUCT
BR-007QWEN332B-005 Qwen3 32B tau2-bench Overall 29.8% Unknown Primary source QWEN-QWEN332B
BR-007QWEN34B-005 Qwen3 4B tau2-bench Overall 19% Unknown Primary source QWEN-QWEN34B
BR-007QWEN34B2507-005 Qwen3 4B 2507 tau2-bench Overall 25.4% Unknown Primary source QWEN-QWEN34B2507
BR-007QWEN34B2507INSTRUCT-005 Qwen3 4B 2507 Instruct tau2-bench Overall 26.6% Unknown Primary source QWEN-QWEN34B2507INSTRUCT
BR-007QWEN3508B-005 Qwen3.5 0.8B tau2-bench Overall 65.2% Unknown Primary source QWEN-QWEN3508B
BR-007QWEN3508B-019 Qwen3.5 0.8B tau2-bench Overall 47.7% Unknown Primary source QWEN-QWEN3508B
BR-007QWEN35122BA10B-005 Qwen3.5 122B A10B tau2-bench Overall 84.5% Unknown Primary source QWEN-QWEN35122BA10B
BR-007QWEN35122BA10B-020 Qwen3.5 122B A10B tau2-bench Overall 93.6% Unknown Primary source QWEN-QWEN35122BA10B
BR-007QWEN3527B-005 Qwen3.5 27B tau2-bench Overall 93.9% Unknown Primary source QWEN-QWEN3527B
BR-007QWEN3527B-018 Qwen3.5 27B tau2-bench Overall 87.1% Unknown Primary source QWEN-QWEN3527B
BR-007QWEN352B-005 Qwen3.5 2B tau2-bench Overall 81.6% Unknown Primary source QWEN-QWEN352B
BR-007QWEN352B-020 Qwen3.5 2B tau2-bench Overall 69% Unknown Primary source QWEN-QWEN352B
BR-007QWEN3535BA3B-005 Qwen3.5 35B A3B tau2-bench Overall 89.2% Unknown Primary source QWEN-QWEN3535BA3B
BR-007QWEN3535BA3B-018 Qwen3.5 35B A3B tau2-bench Overall 86.3% Unknown Primary source QWEN-QWEN3535BA3B
BR-007QWEN35397BA17B-005 Qwen3.5 397B A17B tau2-bench Overall 95.6% Unknown Primary source QWEN-QWEN35397BA17B
BR-007QWEN35397BA17B-022 Qwen3.5 397B A17B tau2-bench Overall 83.9% Unknown Primary source QWEN-QWEN35397BA17B
BR-007QWEN354B-005 Qwen3.5 4B tau2-bench Overall 87.7% Unknown Primary source QWEN-QWEN354B
BR-007QWEN354B-019 Qwen3.5 4B tau2-bench Overall 92.1% Unknown Primary source QWEN-QWEN354B
BR-007QWEN359B-005 Qwen3.5 9B tau2-bench Overall 85.1% Unknown Primary source QWEN-QWEN359B