BlogLLM Benchmark Scores as Published, Side by Side
LVBench: Results as Published
Every result the catalog holds for LVBench: 26 models from 5 developers, read from 8 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 Multimodal UnderstandingMaintainer Zhipu AI and Tsinghua UniversityIntroduced 2024Data version 2026103001, as of 2026-10-30
LVBench tests whether vision-language models can understand very long videos, where the key facts can be spread across more than an hour of footage. It contains about 100 videos averaging over an hour, with roughly 1,500 question-answer pairs across six temporal comprehension tasks. Models are scored on accuracy against human performance.
LVBench
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6 AstraOpenAI, released 2026-09-03 | 87.5% | Google, Gemini 4 Argonchecked 2026-10-29 | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 82.1% | Google, Gemini 3.8 Flash model cardchecked 2026-10-15 | - |
| GPT-5.6 TerraOpenAI, released 2026-07-09 | 78.9% | Google, Gemini 3.7 Flash model cardchecked 2026-10-15; printed on 1 more page | - |
| GPT-5.2OpenAI, released 2025-12-11 | 73.7% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
| Claude Opus 5.5Anthropic, released 2026-09-22 | 83.7% | Google, Gemini 4 Argonchecked 2026-10-29 | - |
| Claude Fable 5.1Anthropic, released 2026-09-01 | 79.7% | Google, Gemini 4 Argonchecked 2026-10-29 | - |
| Claude Opus 5Anthropic, released 2026-07-24 | 75.4% | Google, Gemini 3.8 Flash model cardchecked 2026-10-15 | - |
| Claude Sonnet 5Anthropic, released 2026-06-30 | 68.5% | Google, Gemini 3.7 Flash model cardchecked 2026-10-15; printed on 1 more page | - |
| Claude Opus 4.6Anthropic, released 2026-02-05 | 63% | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15 | Effort: max |
| Claude Opus 4.5Anthropic, released 2025-11-24 | 57.3% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
| Gemini 4 ArgonGoogle, released 2026-09-30 | 91.7% | Google, Gemini 4 Argonchecked 2026-10-29 | - |
| Gemini 3.8 FlashGoogle, released 2026-09-02 | 87.1% | Google, Gemini 3.8 Flash model cardchecked 2026-10-15 | Model setup as reported: Model card results table ("Results as of September, 2026"); effort not stated. Methodology page linked. Value printed as "87.1% (static)". |
| 87.8% | Google, Gemini 3.8 Flash model cardchecked 2026-10-15 | Model setup as reported: Model card results table ("Results as of September, 2026"); effort not stated. Methodology page linked. Value printed as "87.8% (agentic)". | |
| Gemini 3.7 FlashGoogle, released 2026-08-13 | 85.4% | Google, Gemini 3.7 Flash model cardchecked 2026-10-15; printed on 1 more page | - |
| Gemini 3.6 FlashGoogle, released 2026-07-21 | 84.2% | Google, Gemini 3.7 Flash model cardchecked 2026-10-15 | - |
| Gemini 3 ProGoogle, released 2025-11-18 | 76.2% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15; printed on 1 more page | - |
| Qwen3.7-PlusAlibaba, released 2026-06-01 | 76.2% | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15 | - |
| Qwen3.6-35B-A3BAlibaba, released 2026-04-16 | 71.4% | Alibaba, Qwen3.6-35B-A3B model cardchecked 2026-10-15 | - |
| Qwen3.5-122B-A10BAlibaba, released 2026-02-24 | 74.4% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15 | - |
| Qwen3.5-27BAlibaba, released 2026-02-24 | 73.6% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15; printed on 1 more page | - |
| Qwen3.5-35B-A3BAlibaba, released 2026-02-24 | 71.4% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15; printed on 1 more page | - |
| Qwen3.5-397B-A17BAlibaba, released 2026-02-16 | 75.5% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
| Qwen3-VL-235B-A22BAlibaba, released 2025-09-23 | 63.6% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15; printed on 1 more page | - |
| Qwen3-VL-235B-A22B-ThinkingAlibaba, released 2025-09-23 | 63.6% | Moonshot AI, Kimi K2.5 model cardchecked 2026-10-15 | - |
| Qwen3.8-27BAlibaba | 72.4% | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15 | - |
| Qwen3.8-Flash-NextAlibaba | 76.6% | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15 | - |
| Kimi K2.5Moonshot AI, released 2026-01-27 | 75.9% | Moonshot AI, Kimi K2.5 model cardchecked 2026-10-15; printed on 1 more page | - |
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.