| claude-mcp-claude-opus-4-7 |
20260611T173817Z-b143 |
PASS |
1.00 |
— |
634.4k |
185.8s |
| claude-mcp-claude-opus-4-7 |
20260611T173742Z-e5b0 |
PASS |
1.00 |
— |
367.9k |
140.3s |
| claude-mcp-claude-opus-4-7 |
20260611T173715Z-952d |
PASS |
1.00 |
— |
385.1k |
86.1s |
| claude-mcp-claude-opus-4-7 |
20260611T173612Z-adf1 |
fail |
0.50 |
bbox · X off by +25.00mm |
164.7k |
125.9s |
| claude-mcp-claude-opus-4-7 |
20260611T173515Z-14f5 |
PASS |
1.00 |
— |
609.5k |
146.1s |
| openai-direct-gpt-5 |
20260428T214657Z-a74e |
PASS |
1.00 |
— |
2.4k |
18.5s |
| openai-direct-gpt-5 |
20260428T214628Z-9335 |
PASS |
1.00 |
— |
2.6k |
28.8s |
| openai-direct-gpt-5 |
20260428T214604Z-d9c6 |
PASS |
1.00 |
— |
2.5k |
24.5s |
| openai-direct-gpt-5 |
20260428T214539Z-7c48 |
PASS |
1.00 |
— |
2.5k |
25.1s |
| openai-direct-gpt-5 |
20260428T214512Z-f8e2 |
PASS |
1.00 |
— |
2.6k |
26.2s |
| openai-direct-gpt-5-mini |
20260428T214443Z-b783 |
PASS |
1.00 |
— |
2.5k |
17.4s |
| openai-direct-gpt-5-mini |
20260428T214427Z-0107 |
PASS |
1.00 |
— |
2.5k |
16.1s |
| openai-direct-gpt-5-mini |
20260428T214407Z-4b48 |
PASS |
1.00 |
— |
2.4k |
20.1s |
| openai-direct-gpt-5-mini |
20260428T214352Z-6b51 |
PASS |
1.00 |
— |
2.2k |
14.4s |
| openai-direct-gpt-5-mini |
20260428T214332Z-5d4b |
PASS |
1.00 |
— |
2.7k |
20.2s |
| openai-direct-gpt-4o-mini |
20260428T213324Z-074f |
fail |
0.00 |
valid_solid · solid invalid |
1.4k |
14.4s |
| openai-direct-gpt-4o-mini |
20260428T213317Z-42fe |
fail |
0.00 |
valid_solid · solid invalid |
1.2k |
7.2s |
| openai-direct-gpt-4o-mini |
20260428T213307Z-4fcb |
fail |
0.00 |
valid_solid · solid invalid |
1.3k |
10.0s |
| openai-direct-gpt-4o-mini |
20260428T213253Z-5004 |
fail |
0.00 |
valid_solid · solid invalid |
1.4k |
13.3s |
| openai-direct-gpt-4o-mini |
20260428T213240Z-691c |
fail |
0.00 |
valid_solid · solid invalid |
1.4k |
13.1s |
| claude-direct-claude-sonnet-4-6 |
20260428T211951Z-8708 |
PASS |
1.00 |
— |
1.4k |
7.6s |
| claude-direct-claude-sonnet-4-6 |
20260428T211944Z-cde7 |
PASS |
1.00 |
— |
1.4k |
7.0s |
| claude-direct-claude-sonnet-4-6 |
20260428T211937Z-020d |
PASS |
1.00 |
— |
1.3k |
6.7s |
| claude-direct-claude-sonnet-4-6 |
20260428T211929Z-ceee |
PASS |
1.00 |
— |
1.4k |
8.0s |
| claude-direct-claude-sonnet-4-6 |
20260428T211923Z-b6c8 |
PASS |
1.00 |
— |
1.4k |
6.5s |
| claude-direct-claude-opus-4-7 |
20260428T211805Z-fcea |
PASS |
1.00 |
— |
1.6k |
6.4s |
| claude-direct-claude-opus-4-7 |
20260428T211759Z-53fd |
PASS |
1.00 |
— |
1.6k |
6.1s |
| claude-direct-claude-opus-4-7 |
20260428T211752Z-6dc9 |
PASS |
1.00 |
— |
1.6k |
6.7s |
| claude-direct-claude-opus-4-7 |
20260428T211746Z-f1ff |
PASS |
1.00 |
— |
1.6k |
6.5s |
| claude-direct-claude-opus-4-7 |
20260428T211739Z-eb9f |
PASS |
1.00 |
— |
1.6k |
6.9s |
| claude-direct-claude-haiku-4-5-20251001 |
20260428T211714Z-91a3 |
fail |
0.00 |
valid_solid · solid invalid |
1.6k |
4.4s |
| claude-direct-claude-haiku-4-5-20251001 |
20260428T211710Z-2568 |
fail |
0.00 |
valid_solid · solid invalid |
1.7k |
4.4s |
| claude-direct-claude-haiku-4-5-20251001 |
20260428T211705Z-ed63 |
fail |
0.00 |
valid_solid · solid invalid |
1.7k |
4.3s |
| claude-direct-claude-haiku-4-5-20251001 |
20260428T211701Z-9bf2 |
fail |
0.00 |
valid_solid · solid invalid |
1.7k |
4.3s |
| claude-direct-claude-haiku-4-5-20251001 |
20260428T211656Z-a2ef |
fail |
0.00 |
valid_solid · solid invalid |
1.7k |
4.5s |