Other · model
Seed 2.1 Pro benchmark scores
As of 2026-11-22, Seed 2.1 Pro (Other) has measured scores on 10 benchmarks and estimated scores on 67 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 86.3% | estimated ± 3.7 pp, high confidence |
| AA-HLE | 26.6% | estimated ± 7.6 pp, low confidence |
| AA-SciCode | 49.1% | estimated ± 3.1 pp, high confidence |
| Artificial Analysis Intelligence Index | 26.2% | estimated ± 3.0 pp, high confidence |
| GPQA Diamond | 86.2% | estimated ± 12.9 pp, low confidence |
| HLE | 32.7% | estimated ± 5.1 pp, medium confidence |
| LiveCodeBench v6 | 90.9% | estimated ± 1.9 pp, high confidence |
| AA-Omniscience Accuracy | 30.6% | estimated ± 6.7 pp, low confidence |
| Terminal-Bench 2.1 | 71.0% | measured |
| AA Coding Index | 65.8% | estimated ± 4.3 pp, high confidence |
| AA-MMMU-Pro | 80.7% | estimated ± 1.5 pp, high confidence |
| SWE-bench Verified | 80.4% | estimated ± 2.3 pp, high confidence |
| SWE-bench Pro | 60.4% | estimated ± 3.5 pp, high confidence |
| MMLU-Pro | 85.6% | estimated ± 6.5 pp, medium confidence |
| FailureSensorIQ | 64.9% | estimated ± 2.1 pp, high confidence |
| GPQA | 88.3% | estimated ± 2.4 pp, high confidence |
| MMMU | 87.7% | estimated ± 1.7 pp, medium confidence |
| Chess Puzzles | 21.0% | measured |
| AA Terminal-Bench 2.1 | 81.7% | estimated ± 2.6 pp, medium confidence |
| EBR-bench | 10.0% | estimated ± 12.7 pp, low confidence |
| Terminal-Bench 3.0 | 8.5% | estimated ± 9.1 pp, low confidence |
| Furniture Assembly | 27.2% | estimated ± 14.1 pp, low confidence |
| MaxxBench | 41.0% | estimated ± 10.3 pp, low confidence |
| Mystery Game Puzzles | 14.2% | estimated ± 10.3 pp, low confidence |
| NYT Connections | 63.8% | estimated ± 12.6 pp, low confidence |
| ParseBench-1 | 66.8% | estimated ± 8.4 pp, medium confidence |
| Terminal-Bench 4.1 | 8.4% | estimated ± 10.9 pp, low confidence |
| Vals SWE-bench | 80.7% | estimated ± 5.2 pp, medium confidence |
| Terminal-Bench 2.1 (Vals AI) | 60.8% | estimated ± 7.3 pp, medium confidence |
| Bug Hunt Bench | 14.2% | estimated ± 7.2 pp, low confidence |
| DeepSWE | 45.8% | estimated ± 8.7 pp, medium confidence |
| FrontierPhysics | 0.0% | estimated ± 6.1 pp, low confidence |
| SpireClimb | 0.0% | estimated ± 10.3 pp, low confidence |
| StealthMark | 37.5% | estimated ± 9.7 pp, low confidence |
| AA Terminal-Bench 4.0 | 4.3% | estimated ± 11.0 pp, low confidence |
| SkillsBench official leaderboard (BenchFlow) | 49.4% | estimated ± 6.2 pp, medium confidence |
| FACTS Multimodal | 36.6% | estimated ± 5.6 pp, medium confidence |
| ParseBench-2 | 74.5% | estimated ± 5.0 pp, medium confidence |
| CharXiv | 85.4% | measured |
| CharXiv w/o tools | 86.0% | estimated ± 1.2 pp, high confidence |
| ExploitBench | 21.4% | estimated ± 13.4 pp, low confidence |
| AI2D_TEST | 93.5% | estimated ± 0.9 pp, low confidence |
| C-Eval | 93.2% | estimated ± 1.0 pp, medium confidence |
| CountBench | 97.3% | estimated ± 1.3 pp, low confidence |
| DynaMath | 87.1% | estimated ± 0.8 pp, low confidence |
| ERQA | 72.0% | measured |
| MathVision | 92.6% | measured |
| MLVU (M-Avg) | 88.5% | estimated ± 1.5 pp, high confidence |
| MMLU-Redux | 94.9% | estimated ± 0.9 pp, high confidence |
| MMMU-Pro | 81.6% | measured |
| NL2Repo | 47.0% | measured |
| OmniDocBench 1.5 | 91.2% | estimated ± 2.2 pp, high confidence |
| RealWorldQA | 85.6% | estimated ± 1.5 pp, high confidence |
| ScreenSpot Pro | 78.8% | estimated ± 3.6 pp, medium confidence |
| SimpleVQA | 76.0% | estimated ± 7.3 pp, medium confidence |
| SuperGPQA | 70.8% | measured |
| V* | 93.4% | estimated ± 11.2 pp, low confidence |
| Video-MME (w/o subtitle) | 86.3% | estimated ± 1.3 pp, medium confidence |
| Video-MME (with subtitle) | 90.0% | estimated ± 1.9 pp, high confidence |
| VideoMMMU | 86.2% | estimated ± 1.5 pp, medium confidence |
| We-Math | 87.5% | estimated ± 2.1 pp, low confidence |
| MedXpertQA (MM) | 77.9% | estimated ± 2.4 pp, high confidence |
| DAYJOB | 0.4% | estimated ± 6.3 pp, medium confidence |
| DAYJOB Healthcare | 0.1% | estimated ± 6.1 pp, low confidence |
| BlenderWorld (text-only) | 70.6% | estimated ± 4.0 pp, medium confidence |
| Cookie-Bench | 77.3% | estimated ± 2.5 pp, medium confidence |
| BabyVision w/ Python | 89.7% | estimated ± 3.8 pp, low confidence |
| OpenHarmony Bench v1.0 | 54.6% | estimated ± 2.7 pp, high confidence |
| SEC-Bench Pro | 31.8% | estimated ± 12.3 pp, low confidence |
| BabyVision | 73.7% | measured |
| MMVU | 79.3% | estimated ± 2.7 pp, medium confidence |
| PerceptionBench | 55.5% | estimated ± 2.7 pp, medium confidence |
| ZeroBench | 18.0% | measured |
| OCRBench V2 | 72.0% | estimated ± 3.3 pp, high confidence |
| MMMU-Pro w/ Python | 82.8% | estimated ± 2.6 pp, high confidence |
| ExploitBench Internal Port | 0.0% | estimated ± 1.4 pp, low confidence |
| MathVision w/ Python | 96.5% | estimated ± 0.5 pp, medium confidence |