Codex CLI 0.104.0

GPT 5.2 2026-02-24
Score
17.02
PASSED
Pass Rate: 53.8%
go: 100.0% (6 tasks)
go
typescript: 60.0% (5 tasks)
typ
rust: 50.0% (6 tasks)
rus
dart: 33.3% (3 tasks)
dar
zig: 33.3% (3 tasks)
zig
kotlin: 0.0% (3 tasks)
kot

Evaluation Report

Summary

Metric Value
Agent codex
Model gpt-5.2
Reasoning Effort low
Legacy Mode Yes
Timestamp 2026-02-24T145608
Pass Rate 53.8% (14/26)
Weighted Pass Rate 51.1%
Weighted Score 17.02 / 33.29
Duration 2198.7s

Quality Breakdown

  • Clean Passes: 14
  • Partial Passes (timed out but passed): 0
  • Integrity Violations (modified test files): 0
  • Failures: 12

Results by Language

Language Passed Failed Total Pass Rate
dart 1 2 3 33.3%
go 6 0 6 100.0%
kotlin 0 3 3 0.0%
rust 3 3 6 50.0%
typescript 3 2 5 60.0%
zig 1 2 3 33.3%

Results by Tier

Tier Passed Failed Total Pass Rate
core 8 4 12 66.7%
extended 6 8 14 42.9%

Task Results

Task Status Weight Score Duration
dart/future-pool ✘ FAIL 1.46 0.00 54.1s
dart/isolate-pool ✘ FAIL 1.50 0.00 197.1s
dart/reactive-cache ✔ PASS 1.50 1.50 119.7s
go/bank-account ✔ PASS 1.04 1.04 48.6s
go/dining-philosophers ✔ PASS 1.04 1.04 55.1s
go/errgroup-limit ✔ PASS 1.14 1.14 76.8s
go/parallel-letter-frequency ✔ PASS 1.04 1.04 65.4s
go/react ✔ PASS 1.14 1.14 123.9s
go/singleflight ✔ PASS 1.28 1.28 59.0s
kotlin/channel-multiplexer ✘ FAIL 1.50 0.00 142.5s
kotlin/flow-processor ✘ FAIL 1.50 0.00 187.8s
kotlin/lru-cache ✘ FAIL 1.09 0.00 49.6s
rust/circular-buffer ✘ FAIL 1.12 0.00 51.9s
rust/doubly-linked-list ✔ PASS 1.24 1.24 58.1s
rust/generational-arena ✘ FAIL 1.24 0.00 42.4s
rust/macros ✔ PASS 1.50 1.50 33.0s
rust/parallel-letter-frequency ✔ PASS 1.12 1.12 40.6s
rust/regex-lite ✘ FAIL 1.40 0.00 40.2s
typescript/csv-lite ✔ PASS 1.36 1.36 83.4s
typescript/forth ✘ FAIL 1.26 0.00 59.7s
typescript/glob ✔ PASS 1.14 1.14 38.7s
typescript/promise-pool ✘ FAIL 1.20 0.00 41.1s
typescript/react ✔ PASS 1.14 1.14 55.8s
zig/arena-allocator ✘ FAIL 1.50 0.00 173.4s
zig/comptime-json ✘ FAIL 1.50 0.00 244.5s
zig/small-vector ✔ PASS 1.34 1.34 56.4s

Verification

  • Harness Version: v1.6.1
  • Weight Version: 2.0
  • Tasks Hash: blake3:168696ded119da3ea973f15bde9c00151c127b3f54168196a84212827fa1b1f0
  • Results Hash: blake3:dc862f2e46fc051a9b375ba32472e4a25d39fd2aea2effdbf524d7a5568792bc

Generated by SanityHarness on 2026-02-24T145608

Run Statistics

Tasks Passed 14 / 26
Duration 37m
Cost (Est) -
By Language
dart 33%
go 100%
kotlin 0%
rust 50%
typescript 60%
zig 33%