benchgap
Other · model

Ternary Bonsai 2 27B benchmark scores

As of 2026-11-22, Ternary Bonsai 2 27B (Other) has measured scores on 15 benchmarks and estimated scores on 72 more.

BenchmarkScoreSource
AA-GPQA Diamond84.7%estimated ± 4.4 pp, high confidence
AA-HLE26.2%estimated ± 3.9 pp, high confidence
AA-SciCode39.1%estimated ± 3.8 pp, high confidence
AIME2695.8%measured
Artificial Analysis Intelligence Index17.3%estimated ± 6.3 pp, low confidence
CritPt2.1%estimated ± 4.0 pp, high confidence
GDPval-AA13.4%estimated ± 11.0 pp, low confidence
GPQA Diamond85.8%measured
HLE25.7%estimated ± 6.5 pp, medium confidence
IFBench74.0%measured
AA-LCR77.0%measured
LiveCodeBench v690.1%measured
AA-Omniscience Accuracy24.3%estimated ± 8.4 pp, medium confidence
SciCode38.4%estimated ± 3.6 pp, high confidence
Terminal-Bench 2.152.8%measured
BrowseComp66.9%estimated ± 13.0 pp, low confidence
HLE w/ tools32.3%estimated ± 5.5 pp, low confidence
IFEval91.3%measured
LongBench v263.2%estimated ± 5.5 pp, medium confidence
τ²-bench results80.2%measured
AA Coding Index28.8%estimated ± 5.3 pp, medium confidence
AA-MMMU-Pro74.4%estimated ± 2.4 pp, medium confidence
APEX-Agents-AA1.6%estimated ± 11.4 pp, low confidence
SWE-bench Verified60.8%measured
BFCL v461.5%estimated ± 8.5 pp, low confidence
SWE-bench Pro37.2%estimated ± 4.5 pp, high confidence
AA Agentic Index19.5%estimated ± 12.7 pp, low confidence
MMLU-Pro79.0%estimated ± 1.1 pp, high confidence
AA-IFBench62.1%estimated ± 7.4 pp, medium confidence
AIME 202494.5%estimated ± 2.6 pp, high confidence
GPQA85.8%measured
MMLU88.1%estimated ± 4.2 pp, medium confidence
Vals GPQA Diamond85.1%estimated ± 2.1 pp, high confidence
Vals LiveCodeBench86.1%estimated ± 3.4 pp, medium confidence
Vals MMLU-Pro84.3%estimated ± 1.6 pp, high confidence
MATH-50098.8%measured
MMMLU88.1%estimated ± 1.1 pp, medium confidence
MMMU75.8%estimated ± 9.0 pp, medium confidence
AIME 202595.0%measured
AA MMLU-Pro86.6%estimated ± 1.2 pp, low confidence
ARC-AGI-182.2%estimated ± 2.5 pp, medium confidence
ARC-AGI-233.8%estimated ± 9.7 pp, low confidence
Terminal-Bench 3.04.0%estimated ± 9.1 pp, low confidence
FrontierMath v2 (Tiers 1-3)41.1%estimated ± 8.8 pp, medium confidence
Terminal-Bench 4.10.0%estimated ± 10.9 pp, low confidence
Vals SWE-bench50.3%estimated ± 6.6 pp, low confidence
Terminal-Bench 2.1 (Vals AI)47.0%estimated ± 7.3 pp, low confidence
DeepSWE14.9%estimated ± 12.7 pp, low confidence
HLE w/o tools23.7%estimated ± 4.3 pp, high confidence
ARC-AGI-30.0%estimated ± 8.6 pp, low confidence
Vibe Code Bench0.0%estimated ± 8.4 pp, low confidence
CharXiv74.0%estimated ± 3.3 pp, high confidence
CharXiv w/o tools72.2%estimated ± 3.8 pp, medium confidence
AI2D_TEST88.7%estimated ± 1.4 pp, medium confidence
C-Eval92.0%estimated ± 1.2 pp, high confidence
CountBench93.4%estimated ± 3.6 pp, high confidence
DynaMath81.4%estimated ± 1.5 pp, medium confidence
ERQA55.7%estimated ± 4.2 pp, high confidence
HMMT Feb 202596.1%estimated ± 1.9 pp, low confidence
HMMT Feb 202688.6%estimated ± 4.0 pp, high confidence
HMMT Nov 202593.5%estimated ± 3.2 pp, high confidence
MathVision76.8%estimated ± 9.1 pp, medium confidence
MLVU (M-Avg)79.0%estimated ± 4.2 pp, medium confidence
MMAnswerBench84.2%estimated ± 1.3 pp, high confidence
MMLU-Redux89.1%measured
MMMU-Pro44.6%estimated ± 7.6 pp, medium confidence
NL2Repo44.4%estimated ± 3.4 pp, high confidence
OmniDocBench 1.587.9%estimated ± 1.8 pp, medium confidence
RealWorldQA80.1%measured
ScreenSpot Pro58.9%estimated ± 4.8 pp, medium confidence
SimpleVQA56.9%estimated ± 12.3 pp, low confidence
SuperGPQA58.3%estimated ± 4.1 pp, high confidence
V*81.6%estimated ± 10.1 pp, low confidence
Video-MME (with subtitle)79.4%estimated ± 4.6 pp, high confidence
VideoMMMU44.7%estimated ± 9.6 pp, low confidence
We-Math77.3%estimated ± 5.5 pp, low confidence
MedXpertQA (Text)43.2%estimated ± 4.5 pp, low confidence
MMLU-Pro (Arcee)85.4%estimated ± 3.4 pp, medium confidence
React Native Evals71.0%estimated ± 2.7 pp, medium confidence
SWE-Rebench57.0%estimated ± 3.6 pp, low confidence
SimpleQA38.6%estimated ± 13.4 pp, low confidence
LiveCodeBench66.6%estimated ± 14.6 pp, low confidence
IMOAnswerBench74.5%estimated ± 10.7 pp, low confidence
MRCRv285.2%estimated ± 11.3 pp, low confidence
MMLongBench-Doc61.3%estimated ± 2.6 pp, low confidence
RefCOCO (avg)89.3%estimated ± 3.1 pp, medium confidence
OCRBench V256.9%measured