← Back to leaderboard10.0/1010.0/1010.0/1010.0/1010.0/109.0/108.5/108.0/106.0/103.0/102.0/100.0/100.0/100.0/100/100/100/100/100/100/100/100/100/100/103/103/103/103/103/100/100/100/100/100/10
unsloth/gpt-oss-20b-GGUF
https://huggingface.co/unsloth/gpt-oss-20b-GGUF20b14GBF16Unsloth16.6 GB VRAM131k ctxone-shotcalibrationcodingreasoningtool-callingagenticresearch
Average
6.2
/10 over 14 tests
Scores per test
01Basic Instruction Following
5 submissions · last 2026-09-10 23:30:25
04Coding and Debugging
5 submissions · last 2026-09-10 23:30:35
11Large Web Ranking Retrieval
5 submissions · last 2026-09-10 23:33:50
02Requirement Extraction
5 submissions · last 2026-09-10 23:30:30
07Sequential Multi-Tool Reasoning
5 submissions · last 2026-09-10 23:30:45
05Systems Architecture
5 submissions · last 2026-09-10 23:30:39
08Long-Context Contradiction Detection
10 submissions · last 2026-09-10 23:30:57
06Basic Tool Calling
5 submissions · last 2026-09-10 23:30:42
10Full Experiential Agent Test
5 submissions · last 2026-09-10 23:31:04
13Pokemon Lookup + Strategy Synthesis
5 submissions · last 2026-09-10 23:59:46
03Technical Knowledge and Confidence Calibration
5 submissions · last 2026-09-10 23:30:33
12Multi-Category 2025 Movie Research
5 submissions · last 2026-09-10 23:58:57
14Power-of-Two Research + Python Desktop App
5 submissions · last 2026-09-10 23:59:49
15Three.js Scene Construction
5 submissions · last 2026-09-10 23:59:54
Recent submissions
Three.js Scene Construction
ai · anthropic/claude-sonnet-5 · 2026-09-10 23:59:54
Three.js Scene Construction
ai · anthropic/claude-sonnet-5 · 2026-09-10 23:59:54
Three.js Scene Construction
ai · anthropic/claude-sonnet-5 · 2026-09-10 23:59:54
Three.js Scene Construction
ai · anthropic/claude-sonnet-5 · 2026-09-10 23:59:54
Three.js Scene Construction
ai · anthropic/claude-sonnet-5 · 2026-09-10 23:59:54
Power-of-Two Research + Python Desktop App
ai · anthropic/claude-sonnet-5 · 2026-09-10 23:59:49
Power-of-Two Research + Python Desktop App
ai · anthropic/claude-sonnet-5 · 2026-09-10 23:59:49
Power-of-Two Research + Python Desktop App
ai · anthropic/claude-sonnet-5 · 2026-09-10 23:59:49
Power-of-Two Research + Python Desktop App
ai · anthropic/claude-sonnet-5 · 2026-09-10 23:59:49
Power-of-Two Research + Python Desktop App
ai · anthropic/claude-sonnet-5 · 2026-09-10 23:59:49
Pokemon Lookup + Strategy Synthesis
ai · anthropic/claude-sonnet-5 · 2026-09-10 23:59:46
Pokemon Lookup + Strategy Synthesis
ai · anthropic/claude-sonnet-5 · 2026-09-10 23:59:46
Pokemon Lookup + Strategy Synthesis
ai · anthropic/claude-sonnet-5 · 2026-09-10 23:59:46
Pokemon Lookup + Strategy Synthesis
ai · anthropic/claude-sonnet-5 · 2026-09-10 23:59:46
Pokemon Lookup + Strategy Synthesis
ai · anthropic/claude-sonnet-5 · 2026-09-10 23:59:46
Multi-Category 2025 Movie Research
ai · anthropic/claude-sonnet-5 · 2026-09-10 23:58:57
Multi-Category 2025 Movie Research
ai · anthropic/claude-sonnet-5 · 2026-09-10 23:58:57
Multi-Category 2025 Movie Research
ai · anthropic/claude-sonnet-5 · 2026-09-10 23:58:57
Multi-Category 2025 Movie Research
ai · anthropic/claude-sonnet-5 · 2026-09-10 23:58:57
Multi-Category 2025 Movie Research
ai · anthropic/claude-sonnet-5 · 2026-09-10 23:58:57