OpenCode v1.1.36

Gemini 3 Flash 2026-01-25
Score
16.76
PASSED
Pass Rate: 53.8%
go: 83.3% (6 tasks)
go
rust: 83.3% (6 tasks)
rus
typescript: 40.0% (5 tasks)
typ
dart: 33.3% (3 tasks)
dar
kotlin: 33.3% (3 tasks)
kot
zig: 0.0% (3 tasks)
zig

Evaluation Report

Summary

Metric Value
Agent opencode
Model google/antigravity-gemini-3-flash
Reasoning Effort high
MCP Disabled Yes
Timestamp 2026-01-25T155517
Pass Rate 53.8% (14/26)
Weighted Pass Rate 50.3%
Weighted Score 16.76 / 33.29
Duration 3069.0s

Quality Breakdown

  • Clean Passes: 13
  • Partial Passes (timed out but passed): 1
  • Integrity Violations (modified test files): 0
  • Failures: 11

Results by Language

Language Passed Failed Total Pass Rate
dart 1 2 3 33.3%
go 5 1 6 83.3%
kotlin 1 2 3 33.3%
rust 5 1 6 83.3%
typescript 2 3 5 40.0%
zig 0 3 3 0.0%

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 0.00 100.0s
dart/isolate-pool ✔ PASS 1.50 1.50 133.9s
dart/reactive-cache ✘ FAIL 1.50 0.00 116.3s
go/bank-account ✔ PASS 1.04 1.04 32.3s
go/dining-philosophers ✔ PASS 1.04 1.04 61.5s
go/errgroup-limit ✘ FAIL 1.14 0.00 120.4s
go/parallel-letter-frequency ✔ PASS 1.04 1.04 33.0s
go/react ✔ PASS 1.14 1.14 113.9s
go/singleflight ✔ PASS 1.28 1.28 99.9s
kotlin/channel-multiplexer ✔ PASS 1.50 1.50 171.3s
kotlin/flow-processor ✘ FAIL 1.50 0.00 316.4s
kotlin/lru-cache ✘ FAIL 1.09 0.00 52.9s
rust/circular-buffer ✔ PASS 1.12 1.12 70.5s
rust/doubly-linked-list ✔ PASS 1.24 1.24 50.4s
rust/generational-arena ✔ PASS 1.24 1.24 87.9s
rust/macros ✔ PASS 1.50 1.50 97.6s
rust/parallel-letter-frequency ✔ PASS 1.12 1.12 98.1s
rust/regex-lite ✘ FAIL 1.40 0.00 120.7s
typescript/csv-lite ✘ FAIL 1.36 0.00 120.9s
typescript/forth ✘ FAIL 1.26 0.00 120.8s
typescript/glob ⚠ PARTIAL 1.14 0.86 208.4s
typescript/promise-pool ✘ FAIL 1.20 0.00 97.1s
typescript/react ✔ PASS 1.14 1.14 166.1s
zig/arena-allocator ✘ FAIL 1.50 0.00 174.2s
zig/comptime-json ✘ FAIL 1.50 0.00 194.8s
zig/small-vector ✘ FAIL 1.34 0.00 109.6s

Verification

  • Harness Version: v1.5.1-1-g3b5528f
  • Weight Version: 2.0
  • Tasks Hash: blake3:168696ded119da3ea973f15bde9c00151c127b3f54168196a84212827fa1b1f0
  • Results Hash: blake3:2252ce212adc9d31a99f11feded2c95400e034f987ef9d446c1bf786305f942c

Generated by SanityHarness on 2026-01-25T155517

Run Statistics

Tasks Passed 14 / 26
Duration 51m
Cost (Est) -
By Language
dart 33%
go 83%
kotlin 33%
rust 83%
typescript 40%
zig 0%