reasoning benchmark
FullStackBench en
English subset of FullStackBench for evaluating end-to-end software engineering and full-stack development capability.
Updated Aug 11, 2026
Models3
Model coverage3
MetricScore
EvidenceB
FullStackBench en Ranking
Higher score ranks better on this benchmark.
| 1 | AC | 62.6% | 100.0% | 3 | C | |
| 2 | AC | 60.1% | 50.0% | 3 | C | |
| 3 | AC | 58.1% | 0.0% | 3 | C |
FullStackBench en Score Distribution
A closer view of the leading scores on this benchmark.
FullStackBench en Highlights
The leading models and scores on this benchmark.
What is FullStackBench en?
What FullStackBench en measures and how its scores work.
English subset of FullStackBench for evaluating end-to-end software engineering and full-stack development capability.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- FullStackBench en
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- fullstackbench-en|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about FullStackBench en.
Which model scores highest on FullStackBench en?
Qwen3.5-122B-A10B is currently ranked first with 62.6%.
What does FullStackBench en measure?
English subset of FullStackBench for evaluating end-to-end software engineering and full-stack development capability.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.