Codex CLI 0.125.0

GPT-5.5 • 2026-04-24
Score
26.39
PASSED
Pass Rate: 80.8%
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: 66.7% (3 tasks)
dar
zig: 33.3% (3 tasks)
zig

Evaluation Report

Summary

Metric Value
Agent codex
Model gpt-5.5
Reasoning Effort xhigh
Sandbox Yes
Timestamp 2026-04-24T095558
Pass Rate 80.8% (21/26)
Weighted Pass Rate 79.3%
Weighted Score 26.39 / 33.29
Duration 6157.6s

Quality Breakdown

  • Integrity Violations (modified test files): 0
  • Failures: 5
  • Quota-affected tasks: 0
  • Auth-affected tasks: 0
  • Infra-affected tasks: 0

Behavior Telemetry

  • Total self-test commands: 41
  • Tasks with self-testing: 18/26
  • Total toolchain install attempts: 0
  • Tasks with toolchain install attempts: 0/26
  • Total out-of-workspace read attempts: 2
  • Tasks with out-of-workspace read attempts: 1/26
  • Total toolchain search attempts: 2
  • Tasks with toolchain searching: 2/26
  • Total Agent Skills usage signals: 0
  • Tasks with Agent Skills usage: 0/26 (0.0%)
Task Self Tests Self Test Conf. Tool Installs Out-of-Workspace Reads Out-of-Workspace Conf. Toolchain Searches Skills Used Skill Signals
dart/future-pool 1 true 0 0 true 0 false 0
dart/isolate-pool 1 true 0 0 true 0 false 0
dart/reactive-cache 1 true 0 0 true 0 false 0
go/bank-account 2 true 0 0 true 0 false 0
go/dining-philosophers 2 true 0 0 true 0 false 0
go/errgroup-limit 6 true 0 0 true 0 false 0
go/parallel-letter-frequency 1 true 0 0 true 0 false 0
go/react 3 true 0 0 true 0 false 0
go/singleflight 6 true 0 0 true 0 false 0
kotlin/channel-multiplexer 6 true 0 0 true 0 false 0
kotlin/flow-processor 2 true 0 0 true 0 false 0
kotlin/lru-cache 2 true 0 0 true 1 false 0
rust/circular-buffer 1 true 0 0 true 0 false 0
rust/doubly-linked-list 2 true 0 0 true 0 false 0
rust/generational-arena 1 true 0 0 true 0 false 0
rust/macros 2 true 0 0 true 0 false 0
rust/parallel-letter-frequency 1 true 0 0 true 0 false 0
rust/regex-lite 1 true 0 0 true 0 false 0
zig/arena-allocator 0 true 0 2 true 1 false 0

Results by Language

Language Passed Failed Total Pass Rate
dart 2 1 3 66.7%
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 11 3 14 78.6%

Task Results

Task Status Weight Score Duration
dart/future-pool ✘ FAIL 1.46 0.00 296.5s
dart/isolate-pool ✔ PASS 1.50 1.50 574.9s
dart/reactive-cache ✔ PASS 1.50 1.50 423.3s
go/bank-account ✔ PASS 1.04 1.04 104.2s
go/dining-philosophers ✔ PASS 1.04 1.04 125.8s
go/errgroup-limit ✔ PASS 1.14 1.14 223.7s
go/parallel-letter-frequency ✔ PASS 1.04 1.04 37.2s
go/react ✔ PASS 1.14 1.14 193.5s
go/singleflight ✔ PASS 1.28 1.28 127.3s
kotlin/channel-multiplexer ✔ PASS 1.50 1.50 1113.4s
kotlin/flow-processor ✔ PASS 1.50 1.50 306.2s
kotlin/lru-cache ✔ PASS 1.09 1.09 102.9s
rust/circular-buffer ✔ PASS 1.12 1.12 41.5s
rust/doubly-linked-list ✔ PASS 1.24 1.24 138.2s
rust/generational-arena ✔ PASS 1.24 1.24 66.7s
rust/macros ✔ PASS 1.50 1.50 263.2s
rust/parallel-letter-frequency ✔ PASS 1.12 1.12 71.2s
rust/regex-lite ✘ FAIL 1.40 0.00 63.6s
typescript/csv-lite ✔ PASS 1.36 1.36 277.2s
typescript/forth ✔ PASS 1.26 1.26 178.6s
typescript/glob ✔ PASS 1.14 1.14 330.0s
typescript/promise-pool ✘ FAIL 1.20 0.00 108.0s
typescript/react ✔ PASS 1.14 1.14 339.7s
zig/arena-allocator ✔ PASS 1.50 1.50 625.3s
zig/comptime-json ✘ FAIL 1.50 0.00 11.0s
zig/small-vector ✘ FAIL 1.34 0.00 14.2s

Verification

  • Harness Version: v1.8.12-1-g34ba88c
  • Weight Version: 2.1
  • Tasks Hash: blake3:3c951bc4b67b6739ff03d9f42709ffaa3652df423ebc3d8bdf4bf5b0961db82e
  • Results Hash: blake3:e3fed92a2b41b9050b4e8cc3b0a30a255e38614eae3b638ebecac11d2a56a7bb

Generated by SanityHarness on 2026-04-24T095558

Run Statistics

Tasks Passed 21 / 26
Duration 103m
Cost (Est) -
By Language
dart 67%
go 100%
kotlin 100%
rust 83%
typescript 80%
zig 33%