Skip to content

Benchmark

PinchBench · Version/Metric Unspecified

Scores are percentages. Higher is better.

Models measured
5
Scores recorded
5
Sources
1
IQ weight
No weight published

Score distribution

86.2%
Mean
85.6%
Median
4.8%
Std dev
78%
10th percentile
91.9%
90th percentile
78%
Min
78%91.9%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Trinity Large ThinkingTrinity-Large-Thinking Model Card · Model Card labels only ‘PinchBench’· Reported by Arcee AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.91.9%
2Nemotron 3 UltraNeMo Evaluator SDK · official table · version/metric not stated· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.90%
3Nemotron 3 Super 120B A12Bofficial blog prose · OpenClaw · version and metric not specified· Reported by NVIDIA Developer· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.85.6%
4Nemotron 3.5 Lightning 30B A3Bofficial table · version/metric not stated· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.85.4%
5Mercury 2Mercury 2 official PinchBench evaluation · OpenClaw · success rate · version not stated· Reported by Inception Labs· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.78%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.