Codex CLI 0.104.0

GPT 5.3 Codex Spark 2026-02-24
Score
16.83
PASSED
Pass Rate: 53.8%
go: 83.3% (6 tasks)
go
rust: 83.3% (6 tasks)
rus
kotlin: 66.7% (3 tasks)
kot
zig: 33.3% (3 tasks)
zig
typescript: 20.0% (5 tasks)
typ
dart: 0.0% (3 tasks)
dar

Evaluation Report

Summary

Metric Value
Agent codex
Model gpt-5.3-codex-spark
Reasoning Effort low
Legacy Mode Yes
Timestamp 2026-02-24T115712
Pass Rate 53.8% (14/26)
Weighted Pass Rate 50.6%
Weighted Score 16.83 / 33.29
Duration 541.3s

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 0 3 3 0.0%
go 5 1 6 83.3%
kotlin 2 1 3 66.7%
rust 5 1 6 83.3%
typescript 1 4 5 20.0%
zig 1 2 3 33.3%

Results by Tier

Tier Passed Failed Total Pass Rate
core 7 5 12 58.3%
extended 7 7 14 50.0%

Task Results

Task Status Weight Score Duration
dart/future-pool ✘ FAIL 1.46 0.00 24.3s
dart/isolate-pool ✘ FAIL 1.50 0.00 44.9s
dart/reactive-cache ✘ FAIL 1.50 0.00 32.8s
go/bank-account ✔ PASS 1.04 1.04 10.1s
go/dining-philosophers ✔ PASS 1.04 1.04 10.0s
go/errgroup-limit ✘ FAIL 1.14 0.00 15.5s
go/parallel-letter-frequency ✔ PASS 1.04 1.04 8.9s
go/react ✔ PASS 1.14 1.14 15.3s
go/singleflight ✔ PASS 1.28 1.28 11.6s
kotlin/channel-multiplexer ✘ FAIL 1.50 0.00 56.7s
kotlin/flow-processor ✔ PASS 1.50 1.50 44.3s
kotlin/lru-cache ✔ PASS 1.09 1.09 25.5s
rust/circular-buffer ✔ PASS 1.12 1.12 11.2s
rust/doubly-linked-list ✔ PASS 1.24 1.24 8.0s
rust/generational-arena ✔ PASS 1.24 1.24 8.1s
rust/macros ✔ PASS 1.50 1.50 12.4s
rust/parallel-letter-frequency ✔ PASS 1.12 1.12 8.9s
rust/regex-lite ✘ FAIL 1.40 0.00 8.6s
typescript/csv-lite ✘ FAIL 1.36 0.00 13.2s
typescript/forth ✘ FAIL 1.26 0.00 12.9s
typescript/glob ✔ PASS 1.14 1.14 12.2s
typescript/promise-pool ✘ FAIL 1.20 0.00 5.7s
typescript/react ✘ FAIL 1.14 0.00 16.7s
zig/arena-allocator ✘ FAIL 1.50 0.00 50.9s
zig/comptime-json ✘ FAIL 1.50 0.00 56.1s
zig/small-vector ✔ PASS 1.34 1.34 16.6s

Verification

  • Harness Version: v1.6.1
  • Weight Version: 2.0
  • Tasks Hash: blake3:168696ded119da3ea973f15bde9c00151c127b3f54168196a84212827fa1b1f0
  • Results Hash: blake3:363ad55aeb5515be73fb0ba83e12b1fe945f55e0da34a4b7125ca63997148ee5

Generated by SanityHarness on 2026-02-24T115712

Run Statistics

Tasks Passed 14 / 26
Duration 9m
Cost (Est) -
By Language
dart 0%
go 83%
kotlin 67%
rust 83%
typescript 20%
zig 33%