Benchmarks3w ago
OpenThinker2-32B - Arena-Hard-Auto
Arena-Hard-Auto official Gemini-2.5 judged score 3.2 with CI -0.3/0.3
View sourceemilied137799
hi is a open-weight emilied137799 image generation model.
Running this yourself: can likely run on your own machine.
This model is still tracked for research and discovery, but it is excluded from default public rankings until it returns to active status.
---
Quality Score
908
Arena ELO
Unknown
Parameters
---
Context
Sign in to join the discussion
0
Downloads
0
Likes
---
Released
Benchmarks
6
Open Source
1
Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
Arena-Hard-Auto official Gemini-2.5 judged score 3.2 with CI -0.3/0.3
View sourceSWE-Bench Verified resolved rate 66.6
View sourceQuality: 33.1/100 | Price: $1.925/M tokens | Output: 114.399 tok/s | MMLU: 0.832% | HumanEval: 0.859%
LiveCodeBench pass@1 59.4 across 1055 tasks
LiveCodeBench pass@1 78.1 across 1055 tasks
View sourceSWE-Bench Verified resolved rate 66.6
View sourcehi is now available through local Ollama runtime. 4K context window listed. An experimental 1.1B parameter model trained on the new Dolphin 2.8 dataset by Eric Hartford and based on TinyLlama.
Arena-Hard-Auto official Gemini-2.5 judged score 3.2 with CI -0.3/0.3
SWE-Bench Verified resolved rate 66.6
LiveCodeBench pass@1 59.4 across 1055 tasks
LiveCodeBench pass@1 78.1 across 1055 tasks
SWE-Bench Verified resolved rate 66.6