agents benchmark
SkillsBench Leaderboard
SkillsBench evaluates coding agents on self-contained programming tasks, measuring practical engineering skills across diverse software development scenarios.
Updated Aug 17, 2026
Models8
Model coverage8
MetricScore
EvidenceB
SkillsBench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score70.2% | Percentile100.0% | Participants8 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score59.2% | Percentile85.7% | Participants8 | EvidenceC | Evaluated |
| Rank03 | ModelTE | Score55.3% | Percentile71.4% | Participants8 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score54.9% | Percentile57.1% | Participants8 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score48.2% | Percentile42.9% | Participants8 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score45.7% | Percentile28.6% | Participants8 | EvidenceC | Evaluated |
| Rank07 | ModelME | Score44.3% | Percentile14.3% | Participants8 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score28.7% | Percentile0.0% | Participants8 | EvidenceC | Evaluated |
SkillsBench Highlights
The leading models and scores on this benchmark.
SkillsBench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for SkillsBench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis skillsbench 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.
- 01ACQwen3.8 MaxAlibaba Cloud / Qwen Team
- Score
- 70.2%
- Price
- $2.0 input / $6.0 output per 1M tokens
Strengths
- Ranks #1 of 8 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures SkillsBench, not total model capability
- 02ACQwen3.7 MaxAlibaba Cloud / Qwen Team
- Score
- 59.2%
- Price
- $2.5 input / $7.5 output per 1M tokens
- Speed
- Up to 5.8 tok/s via Together
Strengths
- Ranks #2 of 8 compared models
- 86th percentile on this benchmark
- C evidence result
Considerations
- This result measures SkillsBench, not total model capability
- 03TEHy3Tencent
- Score
- 55.3%
Strengths
- Ranks #3 of 8 compared models
- 71th percentile on this benchmark
- C evidence result
Considerations
- This result measures SkillsBench, not total model capability
- 04ACQwen3.7-PlusAlibaba Cloud / Qwen Team
- Score
- 54.9%
- Price
- $0.50 input / $3.0 output per 1M tokens
Strengths
- Ranks #4 of 8 compared models
- 57th percentile on this benchmark
- C evidence result
Considerations
- This result measures SkillsBench, not total model capability
- 05ACQwen3.6-27BAlibaba Cloud / Qwen Team
- Score
- 48.2%
- Price
- $0.60 input / $3.6 output per 1M tokens
- Speed
- Up to 6.1 tok/s via Novita
Strengths
- Ranks #5 of 8 compared models
- 43th percentile on this benchmark
- C evidence result
Considerations
- This result measures SkillsBench, not total model capability
Selection summary
Best AI Models for SkillsBench
Qwen3.8 Max currently leads SkillsBench with 70.2%. 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 SkillsBench?
What SkillsBench measures and how its scores work.
SkillsBench evaluates coding agents on self-contained programming tasks, measuring practical engineering skills across diverse software development scenarios.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- SkillsBench
- Modality
- text
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- skillsbench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about SkillsBench.
Which model scores highest on SkillsBench?
Qwen3.8 Max is currently ranked first with 70.2%.
What does SkillsBench measure?
SkillsBench evaluates coding agents on self-contained programming tasks, measuring practical engineering skills across diverse software development scenarios.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
8 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.