Codex CLI 0.104.0

GPT 5.2 2026-02-24
Score
15.48
PASSED
Pass Rate: 53.8%
go: 83.3% (6 tasks)
go
kotlin: 66.7% (3 tasks)
kot
rust: 50.0% (6 tasks)
rus
typescript: 40.0% (5 tasks)
typ
dart: 33.3% (3 tasks)
dar
zig: 33.3% (3 tasks)
zig

Evaluation Report

Summary

Metric Value
Agent codex
Model gpt-5.2
Reasoning Effort high
Legacy Mode Yes
Timestamp 2026-02-24T151305
Pass Rate 53.8% (14/26)
Weighted Pass Rate 46.5%
Weighted Score 15.48 / 33.29
Duration 4574.4s

Quality Breakdown

  • Clean Passes: 10
  • Partial Passes (timed out but passed): 4
  • Integrity Violations (modified test files): 0
  • Failures: 8

Results by Language

Language Passed Failed Total Pass Rate
dart 1 2 3 33.3%
go 5 1 6 83.3%
kotlin 2 1 3 66.7%
rust 3 3 6 50.0%
typescript 2 3 5 40.0%
zig 1 2 3 33.3%

Results by Tier

Tier Passed Failed Total Pass Rate
core 5 7 12 41.7%
extended 9 5 14 64.3%

Task Results

Task Status Weight Score Duration
dart/future-pool ✘ FAIL 1.46 0.00 808.5s
dart/isolate-pool ✘ FAIL 1.50 0.00 196.8s
dart/reactive-cache ⚠ PARTIAL 1.50 1.12 257.3s
go/bank-account ✔ PASS 1.04 1.04 82.3s
go/dining-philosophers ✔ PASS 1.04 1.04 105.9s
go/errgroup-limit ✘ FAIL 1.14 0.00 120.5s
go/parallel-letter-frequency ✔ PASS 1.04 1.04 65.6s
go/react ✔ PASS 1.14 1.14 222.6s
go/singleflight ✔ PASS 1.28 1.28 138.8s
kotlin/channel-multiplexer ✘ FAIL 1.50 0.00 247.9s
kotlin/flow-processor ⚠ PARTIAL 1.50 1.12 250.6s
kotlin/lru-cache ✔ PASS 1.09 1.09 105.3s
rust/circular-buffer ✔ PASS 1.12 1.12 105.9s
rust/doubly-linked-list ✔ PASS 1.24 1.24 163.6s
rust/generational-arena ✔ PASS 1.24 1.24 80.8s
rust/macros ✘ FAIL 1.50 0.00 89.8s
rust/parallel-letter-frequency ✘ FAIL 1.12 0.00 120.9s
rust/regex-lite ✘ FAIL 1.40 0.00 64.0s
typescript/csv-lite ✘ FAIL 1.36 0.00 120.9s
typescript/forth ✘ FAIL 1.26 0.00 121.0s
typescript/glob ⚠ PARTIAL 1.14 0.86 120.9s
typescript/promise-pool ✘ FAIL 1.20 0.00 72.6s
typescript/react ✔ PASS 1.14 1.14 236.0s
zig/arena-allocator ✘ FAIL 1.50 0.00 244.9s
zig/comptime-json ✘ FAIL 1.50 0.00 244.7s
zig/small-vector ⚠ PARTIAL 1.34 1.01 186.2s

Verification

  • Harness Version: v1.6.1
  • Weight Version: 2.0
  • Tasks Hash: blake3:168696ded119da3ea973f15bde9c00151c127b3f54168196a84212827fa1b1f0
  • Results Hash: blake3:e8c1b427ed8391f65b5b67d6d11d0c623a78c23c8e7c120fe75da3e40bcd83b4

Generated by SanityHarness on 2026-02-24T151305

Run Statistics

Tasks Passed 14 / 26
Duration 76m
Cost (Est) -
By Language
dart 33%
go 83%
kotlin 67%
rust 50%
typescript 40%
zig 33%