Codex CLI 0.104.0

GPT 5.2 2026-02-24
Score
6.45
FAILED
Pass Rate: 26.9%
rust: 66.7% (6 tasks)
rus
kotlin: 33.3% (3 tasks)
kot
zig: 33.3% (3 tasks)
zig
go: 16.7% (6 tasks)
go
dart: 0.0% (3 tasks)
dar
typescript: 0.0% (5 tasks)
typ

Evaluation Report

Summary

Metric Value
Agent codex
Model gpt-5.2
Reasoning Effort xhigh
Legacy Mode Yes
Timestamp 2026-02-24T152633
Pass Rate 26.9% (7/26)
Weighted Pass Rate 19.4%
Weighted Score 6.45 / 33.29
Duration 4742.7s

Quality Breakdown

  • Clean Passes: 1
  • Partial Passes (timed out but passed): 6
  • Integrity Violations (modified test files): 0
  • Failures: 13

Results by Language

Language Passed Failed Total Pass Rate
dart 0 3 3 0.0%
go 1 5 6 16.7%
kotlin 1 2 3 33.3%
rust 4 2 6 66.7%
typescript 0 5 5 0.0%
zig 1 2 3 33.3%

Results by Tier

Tier Passed Failed Total Pass Rate
core 3 9 12 25.0%
extended 4 10 14 28.6%

Task Results

Task Status Weight Score Duration
dart/future-pool ✘ FAIL 1.46 0.00 196.9s
dart/isolate-pool ✘ FAIL 1.50 0.00 197.0s
dart/reactive-cache ✘ FAIL 1.50 0.00 256.7s
go/bank-account ✘ FAIL 1.04 0.00 120.8s
go/dining-philosophers ✘ FAIL 1.04 0.00 120.8s
go/errgroup-limit ✘ FAIL 1.14 0.00 120.9s
go/parallel-letter-frequency ⚠ PARTIAL 1.04 0.78 121.9s
go/react ✘ FAIL 1.14 0.00 300.5s
go/singleflight ✘ FAIL 1.28 0.00 240.5s
kotlin/channel-multiplexer ✘ FAIL 1.50 0.00 252.2s
kotlin/flow-processor ✘ FAIL 1.50 0.00 260.8s
kotlin/lru-cache ⚠ PARTIAL 1.09 0.82 189.8s
rust/circular-buffer ⚠ PARTIAL 1.12 0.84 120.7s
rust/doubly-linked-list ⚠ PARTIAL 1.24 0.93 300.8s
rust/generational-arena ✔ PASS 1.24 1.24 148.5s
rust/macros ✘ FAIL 1.50 0.00 120.9s
rust/parallel-letter-frequency ⚠ PARTIAL 1.12 0.84 121.2s
rust/regex-lite ✘ FAIL 1.40 0.00 89.1s
typescript/csv-lite ✘ FAIL 1.36 0.00 121.0s
typescript/forth ✘ FAIL 1.26 0.00 121.0s
typescript/glob ✘ FAIL 1.14 0.00 120.9s
typescript/promise-pool ✘ FAIL 1.20 0.00 120.9s
typescript/react ✘ FAIL 1.14 0.00 300.9s
zig/arena-allocator ✘ FAIL 1.50 0.00 244.5s
zig/comptime-json ✘ FAIL 1.50 0.00 244.5s
zig/small-vector ⚠ PARTIAL 1.34 1.01 189.0s

Verification

  • Harness Version: v1.6.1
  • Weight Version: 2.0
  • Tasks Hash: blake3:168696ded119da3ea973f15bde9c00151c127b3f54168196a84212827fa1b1f0
  • Results Hash: blake3:eb60db01c97aa9eb8ac9e3781e32dbfb7fba2e129718febc1a59045073f50851

Generated by SanityHarness on 2026-02-24T152633

Run Statistics

Tasks Passed 7 / 26
Duration 79m
Cost (Est) -
By Language
dart 0%
go 17%
kotlin 33%
rust 67%
typescript 0%
zig 33%