LLM Evaluation

← Run of 2025-10-24 15:00:17 / task8_regex_extraction
24
Models Tested
58.3%
Success Rate
1m 5s
Avg Duration
27s - 1m 58s
Duration Range
Score Model Duration Session (KB) test_1_file_exists.sh test_2_valid_json.sh test_3_email_extraction.sh test_4_phone_extraction.sh test_5_url_extraction.sh test_6_date_extraction.sh
100.0% openrouter/openai/gpt-5 1m 26s 347.4 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/openai/gpt-5-nano 1m 55s 504.4 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/anthropic/claude-3.5-sonnet 1m 13s 98.2 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/openai/gpt-4o-mini 1m 21s 216.0 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/openai/gpt-oss-20b 1m 1s 192.4 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/anthropic/claude-3.7-sonnet 43s 62.3 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/anthropic/claude-haiku-4.5 44s 42.0 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/deepseek/deepseek-v3.1-terminus 1m 1s 52.5 ✅ ✅ ✅ ✅ ✅ ✅
100.0% litellm/GLM-4.5-Air-FP8-dev 1m 42s 30.7 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/anthropic/claude-sonnet-4.5 50s 46.7 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/openai/gpt-5-mini 1m 33s 201.0 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/anthropic/claude-3.5-haiku 1m 11s 92.5 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/anthropic/claude-sonnet-4 1m 37s 113.1 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/openai/gpt-4.1-mini 47s 144.2 ✅ ✅ ✅ ✅ ✅ ✅
83.3% openrouter/qwen/qwen3-coder 55s 50.2 ✅ ✅ ✅ ❌ ✅ ✅
83.3% openrouter/x-ai/grok-3-mini 1m 25s 822.6 ✅ ✅ ✅ ✅ ✅ ❌
66.7% openrouter/anthropic/claude-3-haiku 45s 53.1 ✅ ✅ ❌ ✅ ✅ ❌
16.7% openrouter/google/gemini-2.5-flash-preview-09-2025 32s 26.5 ✅ ❌ ❌ ❌ ❌ ❌
16.7% openrouter/openai/gpt-oss-120b 48s 375.6 ✅ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/google/gemini-2.5-pro 59s 14.2 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/google/gemini-2.5-flash-lite-preview-09-2025 1m 58s 38.2 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/deepseek/deepseek-chat-v3-0324 40s 18.5 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/openai/gpt-4.1-nano 28s 21.0 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/qwen/qwen3-14b 27s 55.3 ❌ ❌ ❌ ❌ ❌ ❌