Codex CLI 0.99.0

GPT-5.3 Codex 2026-02-06
Score
21.06
PASSED
Pass Rate: 69.2%
go: 83.3% (6 tasks)
go
rust: 83.3% (6 tasks)
rus
typescript: 80.0% (5 tasks)
typ
kotlin: 66.7% (3 tasks)
kot
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 xhigh
Timestamp 2026-02-06T092708
Pass Rate 69.2% (18/26)
Weighted Pass Rate 63.3%
Weighted Score 21.06 / 33.29
Duration 4187.8s

Quality Breakdown

  • Clean Passes: 15
  • Partial Passes (timed out but passed): 3
  • Integrity Violations (modified test files): 0
  • Failures: 5

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 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 9 3 12 75.0%
extended 9 5 14 64.3%

Task Results

Task Status Weight Score Duration
dart/future-pool ✘ FAIL 1.46 0.00 107.0s
dart/isolate-pool ✘ FAIL 1.50 0.00 196.9s
dart/reactive-cache ⚠ PARTIAL 1.50 1.12 257.3s
go/bank-account ✔ PASS 1.04 1.04 60.1s
go/dining-philosophers ✔ PASS 1.04 1.04 105.6s
go/errgroup-limit ✘ FAIL 1.14 0.00 93.7s
go/parallel-letter-frequency ✔ PASS 1.04 1.04 44.0s
go/react ✔ PASS 1.14 1.14 154.8s
go/singleflight ✔ PASS 1.28 1.28 80.8s
kotlin/channel-multiplexer ✘ FAIL 1.50 0.00 247.6s
kotlin/flow-processor ✔ PASS 1.50 1.50 186.0s
kotlin/lru-cache ✔ PASS 1.09 1.09 79.4s
rust/circular-buffer ✔ PASS 1.12 1.12 42.8s
rust/doubly-linked-list ✔ PASS 1.24 1.24 114.5s
rust/generational-arena ✔ PASS 1.24 1.24 67.3s
rust/macros ✔ PASS 1.50 1.50 61.5s
rust/parallel-letter-frequency ✔ PASS 1.12 1.12 68.3s
rust/regex-lite ✘ FAIL 1.40 0.00 120.7s
typescript/csv-lite ⚠ PARTIAL 1.36 1.02 121.0s
typescript/forth ⚠ PARTIAL 1.26 0.95 581.0s
typescript/glob ✔ PASS 1.14 1.14 57.2s
typescript/promise-pool ✘ FAIL 1.20 0.00 63.9s
typescript/react ✔ PASS 1.14 1.14 685.9s
zig/arena-allocator ✘ FAIL 1.50 0.00 244.3s
zig/comptime-json ✘ FAIL 1.50 0.00 244.4s
zig/small-vector ✔ PASS 1.34 1.34 101.9s

Verification

  • Harness Version: dev
  • Weight Version: 2.0
  • Tasks Hash: blake3:168696ded119da3ea973f15bde9c00151c127b3f54168196a84212827fa1b1f0
  • Results Hash: blake3:4d880114cdf139a13391a4df96a12e24d4c011a34a25babb940c49c622d497db

Generated by SanityHarness on 2026-02-06T092708

Run Statistics

Tasks Passed 18 / 26
Duration 70m
Cost (Est) -
By Language
dart 33%
go 83%
kotlin 67%
rust 83%
typescript 80%
zig 33%