BlogLLM Benchmark Scores as Published, Side by Side
VitaBench: Results as Published
Every result the catalog holds for VitaBench: 14 models from 5 developers, read from 3 pages. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Tool Use and WorkflowsMaintainer Meituan LongCat Team (Wei He and co-authors)Introduced 2025Data version 2026103001, as of 2026-10-30
VitaBench tests agents on interactive tasks taken from food delivery, in-store consumption, and online travel services. The simulation has 66 tools and is split into 100 cross-scenario tasks and 300 single-scenario tasks, each built from real user requests. The agent has to use those tools across a multi-turn conversation, clarify unclear instructions, and follow a user intent that can change. A rubric-based sliding window evaluator judges the outcome, and the reported result is a success rate.
VitaBench
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-5.2OpenAI, released 2025-12-11 | 38.2% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
| GPT-5 miniOpenAI, released 2025-08-07 | 13.9% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15 | - |
| Claude Opus 4.5Anthropic, released 2025-11-24 | 56.3% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
| Gemma 4 26B A4BGoogle, released 2026-04-02 | 36.9% | Alibaba, Qwen3.6-35B-A3B model cardchecked 2026-10-15 | - |
| Gemma 4 31BGoogle, released 2026-04-02 | 43% | Alibaba, Qwen3.6-35B-A3B model cardchecked 2026-10-15 | - |
| Gemini 3 ProGoogle, released 2025-11-18 | 51.6% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
| Qwen3.6-35B-A3BAlibaba, released 2026-04-16 | 35.6% | Alibaba, Qwen3.6-35B-A3B model cardchecked 2026-10-15 | - |
| Qwen3.5-122B-A10BAlibaba, released 2026-02-24 | 33.6% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15 | - |
| Qwen3.5-27BAlibaba, released 2026-02-24 | 41.9% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15; printed on 1 more page | - |
| Qwen3.5-35B-A3BAlibaba, released 2026-02-24 | 31.9% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15; printed on 1 more page | - |
| Qwen3.5-397B-A17BAlibaba, released 2026-02-16 | 49.7% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
| Qwen3-235B-A22BAlibaba, released 2025-04-29 | 31.6% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15 | - |
| Qwen3-Max-ThinkingAlibaba | 40.9% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
| Kimi K2.5Moonshot AI, released 2026-01-27 | 41.9% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.