LLM Evaluation

← Run of 2025-10-24 18:25:03 / task8_regex_extraction
23
Models Tested
69.6%
Success Rate
1m 14s
Avg Duration
33s - 3m 33s
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 17s 275.1 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/openai/gpt-5-nano 1m 41s 489.7 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/openai/gpt-oss-120b 55s 314.1 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/qwen/qwen3-coder 3m 33s 275.9 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/anthropic/claude-3.5-sonnet 1m 1s 69.7 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/google/gemini-2.5-pro 2m 1s 33.9 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/openai/gpt-4o-mini 1m 17s 386.9 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/anthropic/claude-3.7-sonnet 1m 46s 178.9 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/anthropic/claude-haiku-4.5 56s 95.8 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/deepseek/deepseek-v3.1-terminus 1m 6s 39.4 ✅ ✅ ✅ ✅ ✅ ✅
100.0% litellm/GLM-4.5-Air-FP8-dev 2m 18s 76.9 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/anthropic/claude-sonnet-4.5 53s 51.3 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/openai/gpt-5-mini 1m 17s 187.4 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/anthropic/claude-3.5-haiku 47s 57.8 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/anthropic/claude-sonnet-4 1m 13s 83.1 ✅ ✅ ✅ ✅ ✅ ✅
100.0% openrouter/openai/gpt-4.1-mini 1m 3s 285.5 ✅ ✅ ✅ ✅ ✅ ✅
83.3% openrouter/x-ai/grok-3-mini 1m 6s 506.9 ✅ ✅ ✅ ✅ ✅ ❌
66.7% openrouter/anthropic/claude-3-haiku 39s 60.0 ✅ ✅ ❌ ❌ ✅ ✅
66.7% openrouter/openai/gpt-4.1-nano 58s 181.7 ✅ ✅ ❌ ✅ ✅ ❌
16.7% openrouter/google/gemini-2.5-flash-preview-09-2025 50s 19.3 ✅ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/google/gemini-2.5-flash-lite-preview-09-2025 39s 20.5 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/openai/gpt-oss-20b 49s 370.2 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/deepseek/deepseek-chat-v3-0324 33s 15.8 ❌ ❌ ❌ ❌ ❌ ❌