Codex CLI 0.100.0

GPT 5.3 Codex Spark 2026-02-13
Score
24.75
PASSED
Pass Rate: 80.8%
go: 100.0% (6 tasks)
go
kotlin: 100.0% (3 tasks)
kot
typescript: 100.0% (5 tasks)
typ
rust: 83.3% (6 tasks)
rus
dart: 33.3% (3 tasks)
dar
zig: 33.3% (3 tasks)
zig

Evaluation Report

Summary

Metric Value
Agent codex
Model gpt-5.3-codex-spark
Reasoning Effort xhigh
Timestamp 2026-02-13T101043
Pass Rate 80.8% (21/26)
Weighted Pass Rate 74.3%
Weighted Score 24.75 / 33.29
Duration 5068.3s

Quality Breakdown

  • Clean Passes: 17
  • Partial Passes (timed out but passed): 4
  • Integrity Violations (modified test files): 0
  • Failures: 1

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 5 0 5 100.0%
zig 1 2 3 33.3%

Results by Tier

Tier Passed Failed Total Pass Rate
core 11 1 12 91.7%
extended 10 4 14 71.4%

Task Results

Task Status Weight Score Duration
dart/future-pool ✘ FAIL 1.46 0.00 107.2s
dart/isolate-pool ✘ FAIL 1.50 0.00 838.6s
dart/reactive-cache ✔ PASS 1.50 1.50 214.5s
go/bank-account ✔ PASS 1.04 1.04 56.5s
go/dining-philosophers ⚠ PARTIAL 1.04 0.78 122.0s
go/errgroup-limit ⚠ PARTIAL 1.14 0.86 122.3s
go/parallel-letter-frequency ✔ PASS 1.04 1.04 46.1s
go/react ✔ PASS 1.14 1.14 119.3s
go/singleflight ✔ PASS 1.28 1.28 49.2s
kotlin/channel-multiplexer ✔ PASS 1.50 1.50 256.5s
kotlin/flow-processor ✔ PASS 1.50 1.50 165.1s
kotlin/lru-cache ✔ PASS 1.09 1.09 72.0s
rust/circular-buffer ✔ PASS 1.12 1.12 49.5s
rust/doubly-linked-list ✔ PASS 1.24 1.24 71.6s
rust/generational-arena ✔ PASS 1.24 1.24 47.4s
rust/macros ✔ PASS 1.50 1.50 51.8s
rust/parallel-letter-frequency ✔ PASS 1.12 1.12 97.4s
rust/regex-lite ✘ FAIL 1.40 0.00 121.2s
typescript/csv-lite ⚠ PARTIAL 1.36 1.02 561.0s
typescript/forth ✔ PASS 1.26 1.26 528.7s
typescript/glob ✔ PASS 1.14 1.14 64.8s
typescript/promise-pool ⚠ PARTIAL 1.20 0.90 581.4s
typescript/react ✔ PASS 1.14 1.14 129.9s
zig/arena-allocator ✘ FAIL 1.50 0.00 245.2s
zig/comptime-json ✘ FAIL 1.50 0.00 246.2s
zig/small-vector ✔ PASS 1.34 1.34 102.6s

Verification

  • Harness Version: dev
  • Weight Version: 2.0
  • Tasks Hash: blake3:168696ded119da3ea973f15bde9c00151c127b3f54168196a84212827fa1b1f0
  • Results Hash: blake3:2a5628a6db8b37e7a9dece4b3b57cf6865f2404f2dfade7154393bcdb9c52871

Generated by SanityHarness on 2026-02-13T101043

Run Statistics

Tasks Passed 21 / 26
Duration 84m
Cost (Est) -
By Language
dart 33%
go 100%
kotlin 100%
rust 83%
typescript 100%
zig 33%