Codex CLI 0.104.0

GPT 5.3 Codex 2026-02-24
Score
24.73
PASSED
Pass Rate: 76.9%
go: 100.0% (6 tasks)
go
kotlin: 100.0% (3 tasks)
kot
rust: 83.3% (6 tasks)
rus
typescript: 80.0% (5 tasks)
typ
dart: 33.3% (3 tasks)
dar
zig: 33.3% (3 tasks)
zig

Evaluation Report

Summary

Metric Value
Agent codex
Model gpt-5.3-codex
Reasoning Effort high
Legacy Mode Yes
Timestamp 2026-02-24T123832
Pass Rate 76.9% (20/26)
Weighted Pass Rate 74.3%
Weighted Score 24.73 / 33.29
Duration 2694.8s

Quality Breakdown

  • Clean Passes: 20
  • Partial Passes (timed out but passed): 0
  • Integrity Violations (modified test files): 0
  • Failures: 6

Results by Language

Language Passed Failed Total Pass Rate
dart 1 2 3 33.3%
go 6 0 6 100.0%
kotlin 3 0 3 100.0%
rust 5 1 6 83.3%
typescript 4 1 5 80.0%
zig 1 2 3 33.3%

Results by Tier

Tier Passed Failed Total Pass Rate
core 10 2 12 83.3%
extended 10 4 14 71.4%

Task Results

Task Status Weight Score Duration
dart/future-pool ✘ FAIL 1.46 0.00 79.5s
dart/isolate-pool ✘ FAIL 1.50 0.00 147.3s
dart/reactive-cache ✔ PASS 1.50 1.50 180.3s
go/bank-account ✔ PASS 1.04 1.04 61.1s
go/dining-philosophers ✔ PASS 1.04 1.04 68.0s
go/errgroup-limit ✔ PASS 1.14 1.14 104.2s
go/parallel-letter-frequency ✔ PASS 1.04 1.04 25.1s
go/react ✔ PASS 1.14 1.14 104.9s
go/singleflight ✔ PASS 1.28 1.28 59.3s
kotlin/channel-multiplexer ✔ PASS 1.50 1.50 155.6s
kotlin/flow-processor ✔ PASS 1.50 1.50 160.9s
kotlin/lru-cache ✔ PASS 1.09 1.09 347.9s
rust/circular-buffer ✔ PASS 1.12 1.12 42.3s
rust/doubly-linked-list ✔ PASS 1.24 1.24 95.7s
rust/generational-arena ✔ PASS 1.24 1.24 41.8s
rust/macros ✔ PASS 1.50 1.50 40.3s
rust/parallel-letter-frequency ✔ PASS 1.12 1.12 61.6s
rust/regex-lite ✘ FAIL 1.40 0.00 34.2s
typescript/csv-lite ✔ PASS 1.36 1.36 70.2s
typescript/forth ✔ PASS 1.26 1.26 67.7s
typescript/glob ✔ PASS 1.14 1.14 34.9s
typescript/promise-pool ✘ FAIL 1.20 0.00 68.4s
typescript/react ✔ PASS 1.14 1.14 86.8s
zig/arena-allocator ✘ FAIL 1.50 0.00 244.6s
zig/comptime-json ✘ FAIL 1.50 0.00 248.3s
zig/small-vector ✔ PASS 1.34 1.34 64.0s

Verification

  • Harness Version: v1.6.1
  • Weight Version: 2.0
  • Tasks Hash: blake3:168696ded119da3ea973f15bde9c00151c127b3f54168196a84212827fa1b1f0
  • Results Hash: blake3:0ca2dfdf55fed53acf5f596f25ad9f7c864388a9ae087fb41d84894f1b1f314f

Generated by SanityHarness on 2026-02-24T123832

Run Statistics

Tasks Passed 20 / 26
Duration 45m
Cost (Est) -
By Language
dart 33%
go 100%
kotlin 100%
rust 83%
typescript 80%
zig 33%