benchgap
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.

BenchmarkScoreSource
AA-GPQA Diamond86.3%estimated ± 3.7 pp, high confidence
AA-HLE26.6%estimated ± 7.6 pp, low confidence
AA-SciCode49.1%estimated ± 3.1 pp, high confidence
Artificial Analysis Intelligence Index26.2%estimated ± 3.0 pp, high confidence
GPQA Diamond86.2%estimated ± 12.9 pp, low confidence
HLE32.7%estimated ± 5.1 pp, medium confidence
LiveCodeBench v690.9%estimated ± 1.9 pp, high confidence
AA-Omniscience Accuracy30.6%estimated ± 6.7 pp, low confidence
Terminal-Bench 2.171.0%measured
AA Coding Index65.8%estimated ± 4.3 pp, high confidence
AA-MMMU-Pro80.7%estimated ± 1.5 pp, high confidence
SWE-bench Verified80.4%estimated ± 2.3 pp, high confidence
SWE-bench Pro60.4%estimated ± 3.5 pp, high confidence
MMLU-Pro85.6%estimated ± 6.5 pp, medium confidence
FailureSensorIQ64.9%estimated ± 2.1 pp, high confidence
GPQA88.3%estimated ± 2.4 pp, high confidence
MMMU87.7%estimated ± 1.7 pp, medium confidence
Chess Puzzles21.0%measured
AA Terminal-Bench 2.181.7%estimated ± 2.6 pp, medium confidence
EBR-bench10.0%estimated ± 12.7 pp, low confidence
Terminal-Bench 3.08.5%estimated ± 9.1 pp, low confidence
Furniture Assembly27.2%estimated ± 14.1 pp, low confidence
MaxxBench41.0%estimated ± 10.3 pp, low confidence
Mystery Game Puzzles14.2%estimated ± 10.3 pp, low confidence
NYT Connections63.8%estimated ± 12.6 pp, low confidence
ParseBench-166.8%estimated ± 8.4 pp, medium confidence
Terminal-Bench 4.18.4%estimated ± 10.9 pp, low confidence
Vals SWE-bench80.7%estimated ± 5.2 pp, medium confidence
Terminal-Bench 2.1 (Vals AI)60.8%estimated ± 7.3 pp, medium confidence
Bug Hunt Bench14.2%estimated ± 7.2 pp, low confidence
DeepSWE45.8%estimated ± 8.7 pp, medium confidence
FrontierPhysics0.0%estimated ± 6.1 pp, low confidence
SpireClimb0.0%estimated ± 10.3 pp, low confidence
StealthMark37.5%estimated ± 9.7 pp, low confidence
AA Terminal-Bench 4.04.3%estimated ± 11.0 pp, low confidence
SkillsBench official leaderboard (BenchFlow)49.4%estimated ± 6.2 pp, medium confidence
FACTS Multimodal36.6%estimated ± 5.6 pp, medium confidence
ParseBench-274.5%estimated ± 5.0 pp, medium confidence
CharXiv85.4%measured
CharXiv w/o tools86.0%estimated ± 1.2 pp, high confidence
ExploitBench21.4%estimated ± 13.4 pp, low confidence
AI2D_TEST93.5%estimated ± 0.9 pp, low confidence
C-Eval93.2%estimated ± 1.0 pp, medium confidence
CountBench97.3%estimated ± 1.3 pp, low confidence
DynaMath87.1%estimated ± 0.8 pp, low confidence
ERQA72.0%measured
MathVision92.6%measured
MLVU (M-Avg)88.5%estimated ± 1.5 pp, high confidence
MMLU-Redux94.9%estimated ± 0.9 pp, high confidence
MMMU-Pro81.6%measured
NL2Repo47.0%measured
OmniDocBench 1.591.2%estimated ± 2.2 pp, high confidence
RealWorldQA85.6%estimated ± 1.5 pp, high confidence
ScreenSpot Pro78.8%estimated ± 3.6 pp, medium confidence
SimpleVQA76.0%estimated ± 7.3 pp, medium confidence
SuperGPQA70.8%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
VideoMMMU86.2%estimated ± 1.5 pp, medium confidence
We-Math87.5%estimated ± 2.1 pp, low confidence
MedXpertQA (MM)77.9%estimated ± 2.4 pp, high confidence
DAYJOB0.4%estimated ± 6.3 pp, medium confidence
DAYJOB Healthcare0.1%estimated ± 6.1 pp, low confidence
BlenderWorld (text-only)70.6%estimated ± 4.0 pp, medium confidence
Cookie-Bench77.3%estimated ± 2.5 pp, medium confidence
BabyVision w/ Python89.7%estimated ± 3.8 pp, low confidence
OpenHarmony Bench v1.054.6%estimated ± 2.7 pp, high confidence
SEC-Bench Pro31.8%estimated ± 12.3 pp, low confidence
BabyVision73.7%measured
MMVU79.3%estimated ± 2.7 pp, medium confidence
PerceptionBench55.5%estimated ± 2.7 pp, medium confidence
ZeroBench18.0%measured
OCRBench V272.0%estimated ± 3.3 pp, high confidence
MMMU-Pro w/ Python82.8%estimated ± 2.6 pp, high confidence
ExploitBench Internal Port0.0%estimated ± 1.4 pp, low confidence
MathVision w/ Python96.5%estimated ± 0.5 pp, medium confidence