reasoning benchmark
VITA-Bench Leaderboard
VITA-Bench evaluates AI agents on real-world virtual task automation, measuring their ability to complete complex multi-step tasks in simulated environments.
Updated Aug 17, 2026
Models10
Model coverage10
MetricScore
EvidenceB
VITA-Bench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score49.7% | Percentile100.0% | Participants10 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score47.9% | Percentile88.9% | Participants10 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score45.6% | Percentile77.8% | Participants10 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score44.3% | Percentile66.7% | Participants10 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score41.9% | Percentile55.6% | Participants10 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score35.6% | Percentile44.4% | Participants10 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score33.6% | Percentile33.3% | Participants10 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score31.9% | Percentile22.2% | Participants10 | EvidenceC | Evaluated |
| Rank09 | ModelAC | Score29.8% | Percentile11.1% | Participants10 | EvidenceC | Evaluated |
| Rank10 | ModelAC | Score22.0% | Percentile0.0% | Participants10 | EvidenceC | Evaluated |
VITA-Bench Highlights
The leading models and scores on this benchmark.
VITA-Bench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for VITA-Bench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis vita-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.
- 01ACQwen3.5-397B-A17BAlibaba Cloud / Qwen Team
- Score
- 49.7%
- Price
- $0.60 input / $3.6 output per 1M tokens
Strengths
- Ranks #1 of 10 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures VITA-Bench, not total model capability
- 02ACQwen3.7 MaxAlibaba Cloud / Qwen Team
- Score
- 47.9%
- Price
- $2.5 input / $7.5 output per 1M tokens
- Speed
- Up to 5.8 tok/s via Together
Strengths
- Ranks #2 of 10 compared models
- 89th percentile on this benchmark
- C evidence result
Considerations
- This result measures VITA-Bench, not total model capability
- 03ACQwen3.7-PlusAlibaba Cloud / Qwen Team
- Score
- 45.6%
- Price
- $0.50 input / $3.0 output per 1M tokens
Strengths
- Ranks #3 of 10 compared models
- 78th percentile on this benchmark
- C evidence result
Considerations
- This result measures VITA-Bench, not total model capability
- 04ACQwen3.6 PlusAlibaba Cloud / Qwen Team
- Score
- 44.3%
- Price
- $0.50 input / $3.0 output per 1M tokens
- Speed
- Up to 16 tok/s via Together
Strengths
- Ranks #4 of 10 compared models
- 67th percentile on this benchmark
- C evidence result
Considerations
- This result measures VITA-Bench, not total model capability
- 05ACQwen3.5-27BAlibaba Cloud / Qwen Team
- Score
- 41.9%
- Price
- $0.30 input / $2.4 output per 1M tokens
- Speed
- Up to 6.7 tok/s via Novita
Strengths
- Ranks #5 of 10 compared models
- 56th percentile on this benchmark
- C evidence result
Considerations
- This result measures VITA-Bench, not total model capability
Selection summary
Best AI Models for VITA-Bench
Qwen3.5-397B-A17B currently leads VITA-Bench with 49.7%. 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 VITA-Bench?
What VITA-Bench measures and how its scores work.
VITA-Bench evaluates AI agents on real-world virtual task automation, measuring their ability to complete complex multi-step tasks in simulated environments.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- VITA-Bench
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- vita-bench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about VITA-Bench.
Which model scores highest on VITA-Bench?
Qwen3.5-397B-A17B is currently ranked first with 49.7%.
What does VITA-Bench measure?
VITA-Bench evaluates AI agents on real-world virtual task automation, measuring their ability to complete complex multi-step tasks in simulated environments.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
10 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.