gpt-6.1-sol
Benchmark profile · LiveBench 2.0 ·
Results for this model
- Overall benchmark score
- 85.6 / 100
- Cost per task
- $0.6882
- Cost per success
- $0.8044
- Coding
- 96.0 / 100
- Reasoning
- 92.6 / 100
- Browser use
- 93.3 / 100
Costs are based on the benchmark’s 471 shared tasks. Cost per success adjusts the reported cost by the model’s overall score.