503generated behavioral tests
41.7%official best score
0.0%Codex best score
3Codex result rows
Codex Results by Model
| # | Model | Run | Agent | Mode | Score | Eval | Tests | Est. cost | Calls | Wall | Evidence |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | GPT 5.5 (xhigh) | 20260517T094700Z |
Codex /goal | Mini-SWE-compatible no internet | 0.0% | ok | 0/503 | $4.76 | 74 | 0.18h | manifest · eval json · eval summary · usage audit |
| 2 | GPT 5.5 (xhigh) | 20260518T232006Z |
Codex /goal | Paper prompt + /goal no internet | 0.0% | ok | 0/503 | n/a | 57 | 0.21h | not exported |
| 3 | GPT 5.5 (xhigh) | 20260519T215046Z |
Codex /goal | Paper prompt + Goal contract no internet | 0.0% | ok | 0/503 | n/a | 41 | 0.19h | not exported |
Why Scores Differ
Official ProgramBench rows are the public mini-SWE-agent submissions. GoalBench rows are separate Codex /goal submissions. Same model label does not mean the same agent, prompt, tool loop, or generated implementation. A GoalBench row is resolved only when the ProgramBench-scored pass rate is exactly 100%.
GPT 5.5 (xhigh) · 20260517T094700Z
0.0% from 0/503 ProgramBench-scored tests. Raw public eval statuses: not_run: 531.
Agent trace summary unavailable.
Likely miss class: behavioral mismatch.
06dabfabaea7tests.test_advanced_flags.test_profile_creates_valid_pprof_file (not_run)06dabfabaea7tests.test_advanced_flags.test_profile_different_formatters (not_run)06dabfabaea7tests.test_advanced_flags.test_profile_multiple_files (not_run)06dabfabaea7tests.test_advanced_flags.test_profile_with_check_mode (not_run)06dabfabaea7tests.test_advanced_flags.test_profile_with_file_input (not_run)06dabfabaea7tests.test_advanced_flags.test_profile_with_larger_input_captures_data (not_run)
GPT 5.5 (xhigh) · 20260518T232006Z
Public eval evidence has not been exported for this row yet.
GPT 5.5 (xhigh) · 20260519T215046Z
Public eval evidence has not been exported for this row yet.
Official ProgramBench Results by Model
| # | Model | Provider | Score | Cost | Calls |
|---|---|---|---|---|---|
| 1 | GPT 5.5 (high) | OpenAI | 41.7% | $4.27 | 54 |
| 2 | GPT 5.5 | OpenAI | 27.2% | $1.51 | 22 |
| 3 | Claude Sonnet 4.6 | Anthropic | 16.1% | $37.36 | 565 |
| 4 | GPT 5.5 (xhigh) | OpenAI | 13.1% | $9.46 | 80 |
| 5 | GPT 5.4 | OpenAI | 9.3% | $0.33 | 9 |
| 6 | Claude Opus 4.7 (xhigh) | Anthropic | 8.7% | $5.07 | 126 |
| 7 | Gemini 3 Flash | 7.6% | $0.24 | 64 | |
| 8 | Claude Haiku 4.5 | Anthropic | 6.2% | $0.65 | 114 |
| 9 | Claude Opus 4.7 | Anthropic | 4.5% | $0.48 | 20 |
| 10 | Gemini 3.1 Pro | 4.4% | $1.90 | 141 | |
| 11 | GPT 5.4 mini | OpenAI | 2.2% | $0.03 | 8 |
| 12 | GPT 5 mini | OpenAI | 1.2% | $0.02 | 16 |
| 13 | Claude Opus 4.6 | Anthropic | 0.6% | $16.38 | 297 |