agents benchmark
PinchBench Leaderboard
PinchBench evaluates coding agents on real-world agentic coding tasks, measuring both best-case and average performance across complex software engineering scenarios.
Updated Aug 17, 2026
Models6
Model coverage6
MetricScore
EvidenceB
PinchBench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelNV | Score90.0% | Percentile100.0% | Participants6 | EvidenceC | Evaluated |
| Rank02 | ModelNV | Score85.4% | Percentile80.0% | Participants6 | EvidenceC | Evaluated |
| Rank03 | ModelXI | Score81.2% | Percentile60.0% | Participants6 | EvidenceC | Evaluated |
| Rank04 | ModelXI | Score81.0% | Percentile40.0% | Participants6 | EvidenceC | Evaluated |
| Rank05 | ModelZA | Score80.7% | Percentile20.0% | Participants6 | EvidenceC | Evaluated |
| Rank06 | ModelLA | Score68.2% | Percentile0.0% | Participants6 | EvidenceC | Evaluated |
PinchBench Highlights
The leading models and scores on this benchmark.
PinchBench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for PinchBench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis pinchbench AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01NV
- Score
- 90.0%
- Price
- $0.50 input / $2.5 output per 1M tokens
Strengths
- Ranks #1 of 6 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures PinchBench, not total model capability
- 02NV
- Score
- 85.4%
Strengths
- Ranks #2 of 6 compared models
- 80th percentile on this benchmark
- C evidence result
Considerations
- This result measures PinchBench, not total model capability
- 03XIMiMo-V2-OmniXiaomi
- Score
- 81.2%
- Price
- $0.14 input / $0.28 output per 1M tokens
Strengths
- Ranks #3 of 6 compared models
- 60th percentile on this benchmark
- C evidence result
Considerations
- This result measures PinchBench, not total model capability
- 04XIMiMo-V2-ProXiaomi
- Score
- 81.0%
- Price
- $0.43 input / $0.87 output per 1M tokens
Strengths
- Ranks #4 of 6 compared models
- 40th percentile on this benchmark
- C evidence result
Considerations
- This result measures PinchBench, not total model capability
- 05ZAGLM-5V-TurboZhipu AI
- Score
- 80.7%
- Price
- $5.0 input / $22 output per 1M tokens
Strengths
- Ranks #5 of 6 compared models
- 20th percentile on this benchmark
- C evidence result
Considerations
- This result measures PinchBench, not total model capability
Selection summary
Best AI Models for PinchBench
Nemotron 3 Ultra (550B A55B) currently leads PinchBench with 90.0%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is PinchBench?
What PinchBench measures and how its scores work.
PinchBench evaluates coding agents on real-world agentic coding tasks, measuring both best-case and average performance across complex software engineering scenarios.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- PinchBench
- Modality
- text
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- pinchbench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about PinchBench.
Which model scores highest on PinchBench?
Nemotron 3 Ultra (550B A55B) is currently ranked first with 90.0%.
What does PinchBench measure?
PinchBench evaluates coding agents on real-world agentic coding tasks, measuring both best-case and average performance across complex software engineering scenarios.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
6 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.