benchgap
Other · model

MAI-Thinking-1 benchmark scores

As of 2026-11-21, MAI-Thinking-1 (Other) has measured scores on 12 benchmarks and estimated scores on 71 more.

BenchmarkScoreSource
AA-GPQA Diamond82.9%estimated ± 4.4 pp, high confidence
AA-HLE23.6%estimated ± 3.9 pp, high confidence
AA-SciCode46.6%estimated ± 3.6 pp, high confidence
AIME2694.5%measured
Artificial Analysis Intelligence Index17.5%estimated ± 7.4 pp, medium confidence
CritPt1.3%estimated ± 4.0 pp, high confidence
GPQA Diamond84.2%measured
HLE22.8%estimated ± 6.5 pp, medium confidence
IFBench85.0%measured
LiveCodeBench v687.7%measured
AA-Omniscience Accuracy21.9%estimated ± 8.4 pp, medium confidence
SciCode44.6%estimated ± 3.6 pp, high confidence
IFEval95.3%estimated ± 3.6 pp, high confidence
AA Coding Index47.2%estimated ± 5.3 pp, medium confidence
SWE-bench Verified73.5%measured
SWE-bench Pro52.8%measured
MMLU-Pro85.0%measured
AA-IFBench80.4%estimated ± 7.4 pp, low confidence
AIME 202495.5%estimated ± 2.6 pp, high confidence
BBH98.8%estimated ± 2.8 pp, medium confidence
GPQA84.2%measured
MMLU90.6%estimated ± 2.1 pp, medium confidence
Vals GPQA Diamond83.6%estimated ± 2.1 pp, medium confidence
Vals LiveCodeBench86.1%estimated ± 3.4 pp, medium confidence
Vals MMLU-Pro83.4%estimated ± 1.6 pp, medium confidence
MATH-50099.1%estimated ± 2.0 pp, medium confidence
MMMLU87.3%estimated ± 1.1 pp, medium confidence
Chess Puzzles16.0%estimated ± 10.8 pp, low confidence
AIME 202597.0%measured
AA MMLU-Pro86.4%estimated ± 1.2 pp, low confidence
ARC-AGI-179.3%estimated ± 2.5 pp, medium confidence
ARC-AGI-225.3%estimated ± 9.7 pp, low confidence
CursorBench 3.149.7%estimated ± 5.6 pp, low confidence
CursorBench 3.246.2%estimated ± 3.6 pp, medium confidence
EBR-bench9.5%estimated ± 11.3 pp, low confidence
FrontierCode 1.1 Main16.0%estimated ± 4.2 pp, low confidence
FrontierMath v2 (Tier 4)5.3%estimated ± 4.1 pp, low confidence
FrontierMath v2 (Tiers 1-3)34.2%estimated ± 8.8 pp, medium confidence
FrontierSWE v23.1%estimated ± 8.3 pp, low confidence
Furniture Assembly33.3%estimated ± 12.4 pp, low confidence
MaxxBench32.9%estimated ± 5.7 pp, low confidence
Mystery Game Puzzles7.1%estimated ± 13.3 pp, low confidence
Terminal-Bench Hard41.8%estimated ± 4.0 pp, medium confidence
Vals SWE-bench67.4%estimated ± 6.6 pp, medium confidence
Terminal-Bench 2.1 (Vals AI)40.1%estimated ± 6.4 pp, medium confidence
Bug Hunt Bench28.0%estimated ± 12.1 pp, low confidence
CursorBench 4.030.1%estimated ± 3.3 pp, medium confidence
DeepSWE47.7%estimated ± 11.2 pp, low confidence
FrontierCode 2.019.4%estimated ± 6.7 pp, low confidence
FrontierPhysics1.0%estimated ± 4.7 pp, medium confidence
HLE w/o tools20.3%estimated ± 4.3 pp, high confidence
PostTrainBench v1.121.5%estimated ± 4.4 pp, medium confidence
StealthMark14.1%measured
VulcanBench Frontier v475.4%estimated ± 8.3 pp, low confidence
ARC-AGI-30.0%estimated ± 8.6 pp, low confidence
Vibe Code Bench0.7%estimated ± 8.4 pp, medium confidence
FACTS Multimodal39.3%estimated ± 4.7 pp, medium confidence
ExploitBench5.6%estimated ± 12.6 pp, low confidence
C-Eval91.7%estimated ± 1.2 pp, high confidence
HMMT Feb 202593.9%estimated ± 1.8 pp, low confidence
HMMT Feb 202684.9%measured
HMMT Nov 202592.3%estimated ± 2.8 pp, high confidence
MMAnswerBench81.9%estimated ± 1.3 pp, high confidence
MMLU-Redux93.2%estimated ± 0.6 pp, high confidence
NL2Repo35.4%estimated ± 2.8 pp, high confidence
PostTrainBench v117.7%estimated ± 4.6 pp, medium confidence
SuperGPQA67.1%estimated ± 8.5 pp, low confidence
Terminal-Bench 2.046.0%measured
LiveCodeBench Pro77.8%estimated ± 6.0 pp, low confidence
MedXpertQA (Text)40.1%estimated ± 4.5 pp, low confidence
MMLU-Pro (Arcee)84.8%estimated ± 3.4 pp, medium confidence
React Native Evals76.7%estimated ± 2.7 pp, medium confidence
SWE-Rebench57.0%estimated ± 3.6 pp, medium confidence
PostTrainBench19.8%estimated ± 3.7 pp, medium confidence
DAYJOB0.0%estimated ± 3.2 pp, medium confidence
DAYJOB Healthcare0.0%estimated ± 4.7 pp, medium confidence
FrontierCode 1.1 Extended53.4%estimated ± 3.0 pp, low confidence
SimpleQA39.8%estimated ± 11.7 pp, low confidence
LiveCodeBench75.3%estimated ± 14.6 pp, low confidence
OpenHarmony Bench v1.053.3%estimated ± 4.9 pp, low confidence
SEC-Bench Pro13.9%estimated ± 9.3 pp, low confidence
IMOAnswerBench80.4%estimated ± 5.6 pp, medium confidence
ExploitBench Internal Port0.0%estimated ± 6.8 pp, low confidence