Codex CLI 0.104.0

GPT 5.3 Codex 2026-02-24
Score
20.23
PASSED
Pass Rate: 65.4%
go: 100.0% (6 tasks)
go
rust: 83.3% (6 tasks)
rus
typescript: 80.0% (5 tasks)
typ
kotlin: 33.3% (3 tasks)
kot
zig: 33.3% (3 tasks)
zig
dart: 0.0% (3 tasks)
dar

Evaluation Report

Summary

Metric Value
Agent codex
Model gpt-5.3-codex
Reasoning Effort medium
Legacy Mode Yes
Timestamp 2026-02-24T123252
Pass Rate 65.4% (17/26)
Weighted Pass Rate 60.8%
Weighted Score 20.23 / 33.29
Duration 1472.2s

Quality Breakdown

  • Clean Passes: 17
  • Partial Passes (timed out but passed): 0
  • Integrity Violations (modified test files): 0
  • Failures: 9

Results by Language

Language Passed Failed Total Pass Rate
dart 0 3 3 0.0%
go 6 0 6 100.0%
kotlin 1 2 3 33.3%
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 7 7 14 50.0%

Task Results

Task Status Weight Score Duration
dart/future-pool ✘ FAIL 1.46 0.00 47.7s
dart/isolate-pool ✘ FAIL 1.50 0.00 96.5s
dart/reactive-cache ✘ FAIL 1.50 0.00 72.9s
go/bank-account ✔ PASS 1.04 1.04 35.9s
go/dining-philosophers ✔ PASS 1.04 1.04 28.1s
go/errgroup-limit ✔ PASS 1.14 1.14 35.2s
go/parallel-letter-frequency ✔ PASS 1.04 1.04 19.9s
go/react ✔ PASS 1.14 1.14 60.3s
go/singleflight ✔ PASS 1.28 1.28 28.0s
kotlin/channel-multiplexer ✘ FAIL 1.50 0.00 121.3s
kotlin/flow-processor ✘ FAIL 1.50 0.00 107.0s
kotlin/lru-cache ✔ PASS 1.09 1.09 57.5s
rust/circular-buffer ✔ PASS 1.12 1.12 32.0s
rust/doubly-linked-list ✔ PASS 1.24 1.24 31.3s
rust/generational-arena ✔ PASS 1.24 1.24 30.1s
rust/macros ✔ PASS 1.50 1.50 24.5s
rust/parallel-letter-frequency ✔ PASS 1.12 1.12 25.5s
rust/regex-lite ✘ FAIL 1.40 0.00 22.0s
typescript/csv-lite ✔ PASS 1.36 1.36 59.9s
typescript/forth ✔ PASS 1.26 1.26 54.3s
typescript/glob ✔ PASS 1.14 1.14 32.1s
typescript/promise-pool ✘ FAIL 1.20 0.00 15.2s
typescript/react ✔ PASS 1.14 1.14 39.0s
zig/arena-allocator ✘ FAIL 1.50 0.00 137.7s
zig/comptime-json ✘ FAIL 1.50 0.00 227.3s
zig/small-vector ✔ PASS 1.34 1.34 30.8s

Verification

  • Harness Version: v1.6.1
  • Weight Version: 2.0
  • Tasks Hash: blake3:168696ded119da3ea973f15bde9c00151c127b3f54168196a84212827fa1b1f0
  • Results Hash: blake3:c2b97e498c677cc185cff8696c582f39b2af7cfe0996a9662d63ccd21db489b0

Generated by SanityHarness on 2026-02-24T123252

Run Statistics

Tasks Passed 17 / 26
Duration 25m
Cost (Est) -
By Language
dart 0%
go 100%
kotlin 33%
rust 83%
typescript 80%
zig 33%