- GPQA Diamond 88.4
- SuperGPQA 69.6
- HLE (no tool, text only) 25.7
- BeyondAIME 79
- FrontierSci-olympiad 72
- Superchem (text-only) 55
- BABE 57.9
- CL-Bench 20.1
- MultiChallenge 69.9
- WideSearch 70.3
- BrowseComp 64
- ResearchRubrics 59.2
- XPert Bench 56.8
- SkillsBench 43.7
- GDPval 53.1
- FinSearchComp 63.8
- SWE Multilingual 66.6
- SWE-Bench Pro 46.6
- NL2Repo-Bench 28.7
- PaperBench 52.5
- Terminal Bench 2.0 43.3
- MathVision 89.8
- MMMU_Pro 78.4
- HiPhO 83.8
- MedXpertQA-MM 79.6
- BabyVision 64.7
- VLMBias 80.6
- SimpleVQA 72.7
- WorldVQA 50.2
- CharXiv-RQ 82.4 (CharXiv-DQ 94.5) 82.4
- ERQA 71.5
- OSWorld-Verfied 64.4
- MobileWorld 64.6
- VideoMMMU 88.3
- MMVU 76.7
- VideoSimpleQA (VideoSimpleQA-v2 69.0) 71.7
- VideoHolmes 67.4
- Minerva 68.5
- TVBench 80.4
- TOMATO 72.5
- EgoTempo 68.4
- MotionBench 72.4
- VideoMME 89
- VideoMMEv2 (subtitle setting not stated) 64.9
- LongVideoBench 79
- LVBench 76.4
- OVBench 63.2
- OVOBench 75.4
- OmniVideoBench 61.7
- JointAVBench 69.5
- WorldSense 67.3
- MMSU 86.5
- WildSpeech 75.8
- Mean of WenetSpeech test-net 4.47 / test-meeting 5.31 (CER, lower is better) 4.89
- Mean of Librispeech test-clean 1.07 / test-other 2.17 (WER, lower is better) 1.62
- Fleurs (15 langs) (zh/en<->xx) speech translation 74.7
- VideoReasonBench 59.4
- ContPhy 62.4
- Morese-500 34.6
- CGBench 65.5
- VideoEval-Pro 49.5
- ODVBench 66
- LiveSports-3K 78.1
- ViSpeak 87
- CrossVid 63.7
- AVMeme 69.5
Seed2.0 Lite (0428)
Seed2.0 Lite (0428) ranks first on MMSU.
62
Benchmarks with a score
1
Ranked first, out of five or more models
14
In the top three
ByteDance Seed Apr 2026 Seed2.0 Lite (0428)
Closed weights Mid-size
No Epoch Capabilities Index score yet
- MMMU-Pro 78.4% #20 /72
- NL2Repo-Bench 28.7% #26 /28
- SimpleVQA 72.7% #6 /23
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MultiChallenge | 69.9% | #4 of 36 | Model card | |
| WorldSense | 67.3% | #1 of 4 | Model card | |
| SimpleVQA | 72.7% | #6 of 23 | Model card | |
| SuperGPQA | 69.6% | #7 of 26 | Model card | |
| Humanity's Last Exam | 25.7% | #85 of 147 | Model card | |
| WideSearch | 70.3% | #12 of 17 | Model card | |
| Video SimpleQA | 71.7% | #3 of 4 | Model card | |
| CL-bench | 20.1% | #5 of 6 | Model card |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GPQA Diamond | 88.4% | #45 of 284 | Model card | |
| Beyond AIME | 79% | #3 of 14 | Model card | |
| FrontierScience | 72% | #4 of 7 | Model card | |
| HiPhO | 83.8% | #3 of 4 | Model card |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| PaperBench | 52.5% | #4 of 14 | Model card | |
| SWE-bench Multilingual | 66.6% | #50 of 70 | Model card | |
| SWE-Bench Pro | 46.6% | #71 of 77 | Model card | |
| NL2Repo-Bench | 28.7% | #26 of 28 | Model card |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BrowseComp | 64% | #51 of 77 | Model card | |
| OSWorld-Verified | 64.4% | #27 of 37 | Model card | |
| Terminal-Bench 2.0 | 43.3% | #48 of 61 | Model card | |
| ResearchRubrics | 59.2% | #4 of 5 | Model card | |
| SkillsBench | 43.7% | #12 of 13 | Model card | |
| MobileWorld | 64.6% | #3 of 3 | Model card |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MedXpertQA-MM | 79.6% | #2 of 12 | Model card | |
| XpertBench | 56.8% | #2 of 3 | Model card | |
| FinSearchComp | 63.8% | #5 of 7 | Model card | |
| GDPval | 53.1% | #9 of 10 | Model card |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Video-MMMU | 88.3% | #2 of 30 | Model card | |
| Video-MME | 89% | #5 of 42 | Model card | |
| MATH-Vision (MathVision) | 89.8% | #8 of 42 | Model card | |
| ERQA | 71.5% | #5 of 26 | Model card | |
| MMSU | 86.5% | #1 of 5 | Model card | |
| LiveSports-3K | 78.1% | #1 of 4 | Model card | |
| MMMU-Pro | 78.4% | #20 of 72 | Model card | |
| MMVU | 76.7% | #6 of 20 | Model card | |
| CharXiv | 82.4% | #21 of 67 | Model card | |
| MotionBench | 72.4% | #3 of 9 | Model card | |
| MINERVA | 68.5% | #2 of 6 | Model card | |
| CG-Bench | 65.5% | #1 of 3 | Model card | |
| ViSpeak-Bench | 87% | #1 of 3 | Model card | |
| LongVideoBench | 79% | #4 of 11 | Model card | |
| LVBench | 76.4% | #10 of 25 | Model card | |
| EgoTempo | 68.4% | #2 of 5 | Model card | |
| TOMATO | 72.5% | #2 of 5 | Model card | |
| TVBench | 80.4% | #3 of 7 | Model card | |
| Video-Holmes | 67.4% | #3 of 6 | Model card | |
| VideoMME v2 (with subtitles) | 64.9% | #3 of 6 | Model card | |
| VideoEval-Pro | 49.5% | #1 of 2 | Model card | |
| BabyVision | 64.7% | #12 of 20 | Model card | |
| OVO-Bench | 75.4% | #3 of 5 | Model card | |
| VLMsAreBiased | 80.6% | #3 of 5 | Model card | |
| WorldVQA | 50.2% | #6 of 9 | Model card | |
| CrossVid | 63.7% | #2 of 3 | Model card | |
| VideoReasonBench | 59.4% | #2 of 3 | Model card | |
| OVBench | 63.2% | #4 of 5 | Model card | |
| ContPhy | 62.4% | #3 of 3 | Model card | |
| JointAVBench | 69.5% | #2 of 2 | Model card | |
| MORSE-500 | 34.6% | #2 of 2 | Model card | |
| ODV-Bench | 66% | #2 of 2 | Model card | |
| OmniVideoBench | 61.7% | #2 of 2 | Model card | |
| AVMeme Exam | 69.5% | #1 of 1 | Model card |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.