Qwen 3.8 27B ↗
6 measured5 published
- AutomationBenchGB10 · 128GB · UD-Q4_K_XL18.3% ↗
- GPQA DiamondGB10 · 128GB · UD-Q4_K_XL73.2% ↗
- IFBenchGB10 · 128GB · UD-Q4_K_XL42.3% ↗
Find a model.
Follow the evidence.
Local measurements. Published comparisons. Find a setup for your work.
● Measured in our lab◇ Published reference
Where it runs
14 models · 56 results
Claude Fable 5 ↗
0 measured6 published
- GPQA DiamondCloud / API · Published92.6% ↗
- Terminal-BenchCloud / API · Published83.1% ↗
- SWE-bench ProCloud / API · Published80.0% ↗
Claude Fable 5.1 ↗
0 measured1 published
Explore model & setups →Claude Opus 4.8 ↗
0 measured7 published
- GPQA DiamondCloud / API · Published92.0% ↗
- Terminal-BenchCloud / API · Published78.9% ↗
- SWE-bench ProCloud / API · Published69.2% ↗
Claude Opus 5 ↗
0 measured2 published
Explore model & setups →DeepSeek V4 Flash 0731 ↗
0 measured2 published
- Terminal-BenchSetup unspecified · Published82.7% ↗
- AutomationBenchSetup unspecified · Published25.1% ↗
Gemini 3.1 Pro Preview ↗
0 measured5 published
- GPQA DiamondCloud / API · Published94.3% ↗
- Terminal-BenchCloud / API · Published70.7% ↗
- SWE-bench ProCloud / API · Published54.2% ↗
Gemini 3.8 Flash ↗
0 measured2 published
Explore model & setups →GLM-5.3-Flash ↗
0 measured2 published
- Terminal-BenchSetup unspecified · Published84.3% ↗
- AutomationBenchSetup unspecified · Published48.8% ↗
GLM-5.3-Flash NVFP4 ↗
0 measured3 published
- Terminal-BenchSetup unspecified · Published83.2% ↗
- IFBenchSetup unspecified · Published60.5% ↗
- GPQA DiamondSetup unspecified · Published92.1% ↗
GPT-5.6 Luna ↗
0 measured3 published
- GPQA DiamondCloud / API · Published92.3% ↗
- Terminal-BenchCloud / API · Published84.7% ↗
- SWE-bench ProCloud / API · Published62.7% ↗
GPT-5.6 Sol ↗
0 measured6 published
- GPQA DiamondCloud / API · Published94.6% ↗
- Terminal-BenchCloud / API · Published88.8% ↗
- SWE-bench ProCloud / API · Published64.6% ↗
GPT-5.6 Terra ↗
0 measured4 published
- GPQA DiamondCloud / API · Published92.9% ↗
- Terminal-BenchCloud / API · Published87.4% ↗
- SWE-bench ProCloud / API · Published63.4% ↗
GPT-6 Astra ↗
0 measured2 published
Explore model & setups →