LLM Evaluation

← Run of 2025-10-23 23:29:00 / task8_regex_extraction
24
Models Tested
0.0%
Success Rate
1m 28s
Avg Duration
20s - 5m 0s
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
0.0% openrouter/google/gemini-2.5-flash-preview-09-2025 32s 40.2 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/openai/gpt-5 1m 23s 288.5 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/openai/gpt-5-nano 3m 33s 877.7 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/anthropic/claude-3-haiku 40s 67.6 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/openai/gpt-oss-120b 2m 23s 841.4 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/qwen/qwen3-coder 1m 10s 65.2 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/x-ai/grok-3-mini 1m 18s 1014.8 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/anthropic/claude-3.5-sonnet 56s 90.6 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/google/gemini-2.5-pro 1m 16s 45.5 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/openai/gpt-4o-mini 43s 146.7 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/google/gemini-2.5-flash-lite-preview-09-2025 42s 65.6 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/openai/gpt-oss-20b 1m 30s 705.4 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/anthropic/claude-3.7-sonnet 2m 2s 208.1 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/anthropic/claude-haiku-4.5 24s 54.3 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/deepseek/deepseek-v3.1-terminus 1m 16s 73.9 ❌ ❌ ❌ ❌ ❌ ❌
0.0% litellm/GLM-4.5-Air-FP8-dev 5m 0s 0.0 — — — — — —
0.0% openrouter/anthropic/claude-sonnet-4.5 49s 65.6 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/deepseek/deepseek-chat-v3-0324 29s 50.6 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/openai/gpt-4.1-nano 23s 49.3 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/openai/gpt-5-mini 1m 5s 214.3 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/qwen/qwen3-14b 20s 71.5 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/anthropic/claude-3.5-haiku 5m 0s 0.0 — — — — — —
0.0% openrouter/anthropic/claude-sonnet-4 1m 30s 124.7 ❌ ❌ ❌ ❌ ❌ ❌
0.0% openrouter/openai/gpt-4.1-mini 59s 216.0 ❌ ❌ ❌ ❌ ❌ ❌