BlogLLM Benchmark Scores as Published, Side by Side
Qwen3-VL-8B-Thinking: Benchmark Scores as Published
Every result the catalog holds for Qwen3-VL-8B-Thinking: 10 tests in 2 areas, from 1 page. Each was printed by the company named beside it. Each number is as printed; nothing is ranked or rescored.
Developer AlibabaReleased 2025-10-15Context window 256KInput Text, imageOutput TextWeights Open (Apache 2.0)Data version 2026103001, as of 2026-10-30
Computer Use
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| ScreenSpot-v2 | 93.3% | Microsoft, Microsoft Phi-4-reasoning-vision-15B model cardchecked 2026-10-15 | Effort: thinking; Harness: VLMEvalKit; Context: 4096 |
| 92.7% | Microsoft, Microsoft Phi-4-reasoning-vision-15B model cardchecked 2026-10-15 | Effort: thinking; Harness: VLMEvalKit; Context: 40960 |
Multimodal Understanding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| MMMU (validation) | 65.3% | Microsoft, Microsoft Phi-4-reasoning-vision-15B model cardchecked 2026-10-15 | Effort: thinking; Harness: VLMEvalKit; Context: 40960 |
| 59.3% | Microsoft, Microsoft Phi-4-reasoning-vision-15B model cardchecked 2026-10-15 | Effort: thinking; Harness: VLMEvalKit; Context: 4096 | |
| MathVista (testmini) | 79.5% | Microsoft, Microsoft Phi-4-reasoning-vision-15B model cardchecked 2026-10-15 | Effort: thinking; Harness: VLMEvalKit; Context: 40960 |
| 77.7% | Microsoft, Microsoft Phi-4-reasoning-vision-15B model cardchecked 2026-10-15 | Effort: thinking; Harness: VLMEvalKit; Context: 4096 | |
| AI2D (test) | 83.9% | Microsoft, Microsoft Phi-4-reasoning-vision-15B model cardchecked 2026-10-15 | Effort: thinking; Harness: VLMEvalKit; Context: 40960 |
| 83.5% | Microsoft, Microsoft Phi-4-reasoning-vision-15B model cardchecked 2026-10-15 | Effort: thinking; Harness: VLMEvalKit; Context: 4096 | |
| OCRBench | 81.2% | Microsoft, Microsoft Phi-4-reasoning-vision-15B model cardchecked 2026-10-15 | Effort: thinking; Harness: VLMEvalKit; Context: 4096 |
| 82% | Microsoft, Microsoft Phi-4-reasoning-vision-15B model cardchecked 2026-10-15 | Effort: thinking; Harness: VLMEvalKit; Context: 40960 | |
| HallusionBench | 71.6% | Microsoft, Microsoft Phi-4-reasoning-vision-15B model cardchecked 2026-10-15 | Effort: thinking; Harness: VLMEvalKit; Context: 4096 |
| 73% | Microsoft, Microsoft Phi-4-reasoning-vision-15B model cardchecked 2026-10-15 | Effort: thinking; Harness: VLMEvalKit; Context: 40960 | |
| MMStar | 69.3% | Microsoft, Microsoft Phi-4-reasoning-vision-15B model cardchecked 2026-10-15 | Effort: thinking; Harness: VLMEvalKit; Context: 4096 |
| 72.3% | Microsoft, Microsoft Phi-4-reasoning-vision-15B model cardchecked 2026-10-15 | Effort: thinking; Harness: VLMEvalKit; Context: 40960 | |
| ChartQA | 78% | Microsoft, Microsoft Phi-4-reasoning-vision-15B model cardchecked 2026-10-15 | Effort: thinking; Harness: VLMEvalKit; Context: 4096 |
| 78.6% | Microsoft, Microsoft Phi-4-reasoning-vision-15B model cardchecked 2026-10-15 | Effort: thinking; Harness: VLMEvalKit; Context: 40960 | |
| MathVerse (mini) | 67.3% | Microsoft, Microsoft Phi-4-reasoning-vision-15B model cardchecked 2026-10-15 | Effort: thinking; Harness: VLMEvalKit; Context: 4096 |
| 73.3% | Microsoft, Microsoft Phi-4-reasoning-vision-15B model cardchecked 2026-10-15 | Effort: thinking; Harness: VLMEvalKit; Context: 40960 | |
| MathVision (mini) | 43.1% | Microsoft, Microsoft Phi-4-reasoning-vision-15B model cardchecked 2026-10-15 | Effort: thinking; Harness: VLMEvalKit; Context: 4096 |
| 50.7% | Microsoft, Microsoft Phi-4-reasoning-vision-15B model cardchecked 2026-10-15 | Effort: thinking; Harness: VLMEvalKit; Context: 40960 |
More from Alibaba
- Qwen3.8-Max
- Qwen3.7-Plus
- Qwen3.6-27B
- Qwen3.6-35B-A3B
- Qwen3.6-Plus
- Qwen3.5-122B-A10B
- Qwen3.5-27B
- Qwen3.5-35B-A3B
- Qwen3.5-397B-A17B
- Qwen3-VL-32B-Instruct
- Qwen3-VL-32B-Thinking
- Qwen3-VL-8B-Instruct
- Qwen3-VL-235B-A22B
- Qwen3-VL-235B-A22B-Thinking
- Qwen3-Next-80B-A3B
- Qwen3-30B-A3B-Instruct-2507
- Qwen3-30B-A3B-Thinking-2507
- Qwen3-Coder-Plus
- Qwen3-235B-A22B
- Qwen3-32B
- Qwen3-8B
- QwQ-32B-Preview
- Qwen-Max
- Qwen3-Max-Thinking
- Qwen3.7-Max
- Qwen3.8-2.4T-A95B
- Qwen3.8-27B
- Qwen3.8-Flash-Next
Every number here is read from the same catalog file as the benchmark table, data version 2026103001. Where one page printed the 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.