reasoning benchmark
t2-bench Leaderboard
t2-bench is a benchmark for evaluating agentic tool use capabilities, measuring how well models can select, sequence, and utilize tools to solve complex tasks. It tests autonomous planning and execution in multi-step scenarios.
Updated Aug 17, 2026
Models23
Model coverage23
MetricScore
EvidenceB
t2-bench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelGO | Score99.3% | Percentile100.0% | Participants23 | EvidenceC | Evaluated |
| Rank02 | ModelGO | Score90.2% | Percentile95.5% | Participants23 | EvidenceC | Evaluated |
| Rank03 | ModelZA | Score89.7% | Percentile90.9% | Participants23 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score86.7% | Percentile86.4% | Participants23 | EvidenceC | Evaluated |
| Rank05 | ModelGO | Score86.4% | Percentile81.8% | Participants23 | EvidenceC | Evaluated |
| Rank06 | ModelGO | Score85.5% | Percentile77.3% | Participants23 | EvidenceC | Evaluated |
| Rank07 | ModelGO | Score85.4% | Percentile72.7% | Participants23 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score81.2% | Percentile68.2% | Participants23 | EvidenceC | Evaluated |
| Rank09 | ModelDE | Score80.3% | Percentile63.6% | Participants23 | EvidenceC | Evaluated |
| Rank10 | ModelDE | Score80.3% | Percentile59.1% | Participants23 | EvidenceC | Evaluated |
| Rank11 | ModelDE | Score80.2% | Percentile54.5% | Participants23 | EvidenceC | Evaluated |
| Rank12 | ModelAC | Score79.9% | Percentile50.0% | Participants23 | EvidenceC | Evaluated |
| Rank13 | ModelAC | Score79.5% | Percentile45.5% | Participants23 | EvidenceC | Evaluated |
| Rank14 | ModelAC | Score79.1% | Percentile40.9% | Participants23 | EvidenceC | Evaluated |
| Rank15 | ModelAC | Score79.0% | Percentile36.4% | Participants23 | EvidenceC | Evaluated |
| Rank16 | ModelAC | Score74.8% | Percentile31.8% | Participants23 | EvidenceC | Evaluated |
| Rank17 | ModelLA | Score73.2% | Percentile27.3% | Participants23 | EvidenceC | Evaluated |
| Rank18 | ModelOP | Score63.9% | Percentile22.7% | Participants23 | EvidenceC | Evaluated |
| Rank19 | ModelGO | Score57.5% | Percentile18.2% | Participants23 | EvidenceC | Evaluated |
| Rank20 | ModelGO | Score56.2% | Percentile13.6% | Participants23 | EvidenceC | Evaluated |
| Rank21 | ModelAC | Score48.8% | Percentile9.1% | Participants23 | EvidenceC | Evaluated |
| Rank22 | ModelGO | Score29.4% | Percentile4.5% | Participants23 | EvidenceC | Evaluated |
| Rank23 | ModelAC | Score11.6% | Percentile0.0% | Participants23 | EvidenceC | Evaluated |
t2-bench Highlights
The leading models and scores on this benchmark.
t2-bench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for t2-bench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis t2-bench AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01GOGemini 3.1 ProGoogle
- Score
- 99.3%
- Price
- $2.0 input / $12 output per 1M tokens
- Speed
- Up to 23 tok/s via Google
Strengths
- Ranks #1 of 23 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures t2-bench, not total model capability
- 02GOGemini 3 FlashGoogle
- Score
- 90.2%
- Price
- $0.50 input / $3.0 output per 1M tokens
- Speed
- Up to 65 tok/s via Google
Strengths
- Ranks #2 of 23 compared models
- 95th percentile on this benchmark
- C evidence result
Considerations
- This result measures t2-bench, not total model capability
- 03ZAGLM-5Zhipu AI
- Score
- 89.7%
- Price
- $1.0 input / $3.2 output per 1M tokens
- Speed
- Up to 30 tok/s via ZAI
Strengths
- Ranks #3 of 23 compared models
- 91th percentile on this benchmark
- C evidence result
Considerations
- This result measures t2-bench, not total model capability
- 04ACQwen3.5-397B-A17BAlibaba Cloud / Qwen Team
- Score
- 86.7%
- Price
- $0.60 input / $3.6 output per 1M tokens
Strengths
- Ranks #4 of 23 compared models
- 86th percentile on this benchmark
- C evidence result
Considerations
- This result measures t2-bench, not total model capability
- 05GOGemma 4 31BGoogle
- Score
- 86.4%
- Speed
- Up to 8.3 tok/s via FriendliAI
Strengths
- Ranks #5 of 23 compared models
- 82th percentile on this benchmark
- C evidence result
Considerations
- This result measures t2-bench, not total model capability
Selection summary
Best AI Models for t2-bench
Gemini 3.1 Pro currently leads t2-bench with 99.3%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is t2-bench?
What t2-bench measures and how its scores work.
t2-bench is a benchmark for evaluating agentic tool use capabilities, measuring how well models can select, sequence, and utilize tools to solve complex tasks. It tests autonomous planning and execution in multi-step scenarios.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- t2-bench
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- t2-bench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about t2-bench.
Which model scores highest on t2-bench?
Gemini 3.1 Pro is currently ranked first with 99.3%.
What does t2-bench measure?
t2-bench is a benchmark for evaluating agentic tool use capabilities, measuring how well models can select, sequence, and utilize tools to solve complex tasks. It tests autonomous planning and execution in multi-step scenarios.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
23 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.