OpenCode v1.2.9

Claude Sonnet 4.6 2026-02-19
Score
17.53
PASSED
Pass Rate: 57.7%
go: 100.0% (6 tasks)
go
kotlin: 66.7% (3 tasks)
kot
rust: 66.7% (6 tasks)
rus
typescript: 60.0% (5 tasks)
typ
dart: 0.0% (3 tasks)
dar
zig: 0.0% (3 tasks)
zig

Evaluation Report

Summary

Metric Value
Agent opencode
Model azure-claude/claude-sonnet-4-6
MCP Disabled Yes
Sandbox Yes
Legacy Mode Yes
Timestamp 2026-02-19T141016
Pass Rate 57.7% (15/26)
Weighted Pass Rate 52.7%
Weighted Score 17.53 / 33.29
Duration 342.0s

Quality Breakdown

  • Clean Passes: 15
  • Partial Passes (timed out but passed): 0
  • Integrity Violations (modified test files): 0
  • Failures: 11

Results by Language

Language Passed Failed Total Pass Rate
dart 0 3 3 0.0%
go 6 0 6 100.0%
kotlin 2 1 3 66.7%
rust 4 2 6 66.7%
typescript 3 2 5 60.0%
zig 0 3 3 0.0%

Results by Tier

Tier Passed Failed Total Pass Rate
core 8 4 12 66.7%
extended 7 7 14 50.0%

Task Results

Task Status Weight Score Duration
dart/future-pool ✘ FAIL 1.46 0.00 0.0s
dart/isolate-pool ✘ FAIL 1.50 0.00 0.0s
dart/reactive-cache ✘ FAIL 1.50 0.00 0.0s
go/bank-account ✔ PASS 1.04 1.04 0.0s
go/dining-philosophers ✔ PASS 1.04 1.04 40.6s
go/errgroup-limit ✔ PASS 1.14 1.14 0.0s
go/parallel-letter-frequency ✔ PASS 1.04 1.04 0.0s
go/react ✔ PASS 1.14 1.14 0.0s
go/singleflight ✔ PASS 1.28 1.28 0.0s
kotlin/channel-multiplexer ✘ FAIL 1.50 0.00 0.0s
kotlin/flow-processor ✔ PASS 1.50 1.50 0.0s
kotlin/lru-cache ✔ PASS 1.09 1.09 0.0s
rust/circular-buffer ✔ PASS 1.12 1.12 28.8s
rust/doubly-linked-list ✔ PASS 1.24 1.24 0.0s
rust/generational-arena ✔ PASS 1.24 1.24 0.0s
rust/macros ✘ FAIL 1.50 0.00 32.0s
rust/parallel-letter-frequency ✔ PASS 1.12 1.12 0.0s
rust/regex-lite ✘ FAIL 1.40 0.00 0.0s
typescript/csv-lite ✘ FAIL 1.36 0.00 0.0s
typescript/forth ✔ PASS 1.26 1.26 0.0s
typescript/glob ✔ PASS 1.14 1.14 0.0s
typescript/promise-pool ✘ FAIL 1.20 0.00 0.0s
typescript/react ✔ PASS 1.14 1.14 0.0s
zig/arena-allocator ✘ FAIL 1.50 0.00 0.0s
zig/comptime-json ✘ FAIL 1.50 0.00 240.6s
zig/small-vector ✘ FAIL 1.34 0.00 0.0s

Verification

  • Harness Version: v1.5.17-6-g6362fe6-dirty
  • Weight Version: 2.0
  • Tasks Hash: blake3:168696ded119da3ea973f15bde9c00151c127b3f54168196a84212827fa1b1f0
  • Results Hash: blake3:743979de5bf12342023072c881fe5445e62e1fac756ec8414e3f9762e830bb91

Generated by SanityHarness on 2026-02-19T141016

Run Statistics

Tasks Passed 15 / 26
Duration 6m
Cost (Est) -
By Language
dart 0%
go 100%
kotlin 67%
rust 67%
typescript 60%
zig 0%