Seven-case exploratory stack matrix

The operational rows used the same seven cases and scoring fields, but different models and stack configurations. This is stack-level evidence, not a same-model harness attribution test.

Exploratory actual result28 August 2026

Share of the 7 cases each stack passed

Ollama passed 5 of the 7 cases, Flywheel serve 4 and OpenAI Codex 0, each on its own model and stack configuration.

  • Share of the 7 cases passed
  • Did not run, so it has no score

Share of the 7 cases passed. The scale starts at zero.

Ollama

Qwen 2.5 7B, 5 of 7 cases passed

71.4%

Flywheel serve

Flywheel 14B adapter, 4 of 7 cases passed

57.1%

OpenAI Codex

GPT-5.3 Codex Spark, 0 of 7 cases passed

0%

Claude Code

Could not run (quota or rate limit)

No score

OpenCode

Skipped (no endpoint configured)

No score

This is stack-level evidence, not a same-model harness attribution test. Claude Code and OpenCode did not run and are not drawn as zero.

How we know: the matrix
What this does not prove
This matrix does not prove general model or harness quality, market leadership, causal Flywheel advantage, production reliability, or independent validation.
Limitations
Exploratory single-run matrix with seven custom cases. The compared rows use different models and stack configurations; this is not a same-model harness attribution test. Hardware, runtime versions, cost, and resource use are not recorded in the source artifact. Claude was nonoperational and OpenCode was skipped, so neither is plotted or scored as zero.
Method
Same seven cases and scoring fields; different harness stacks and different requested models.
Environment
not recorded in source artifact
Denominator
7 custom cases per operational row
Operational rows

Scroll sideways for more columns.

Text equivalent for the three operational rows.
StackBackendModelPassed / nPass rateMean qualityMean latencyError rateFailure classes
Flywheel servem7-source-mined-serve14b-cpt-adapter4/757.1%0.63930,926.429 ms0%none: 7
Ollamam7-source-mined-ollama:qwen2.5:7bqwen2.5:7b5/771.4%0.6231,361.571 ms0%none: 7
OpenAI Codexcodex-plangpt-5.3-codex-spark0/70%0.28484,466.286 ms0%low_task_focus: 5; none: 2
Unavailable rows
Systems excluded from numeric ranking rather than represented as zero.
SystemStatusReason
Claude CodeNOT OPERATIONALquota_or_rate_limit; requested-model metadata is not treated as valid
OpenCodeSKIPPEDno configured endpoint backend for provider=opencode modes=plan,api,provider,cloud
Source SHA-256
dcac28e8729d2255f3feb647c76ec00d5a975f8b616e947b92e827daf15002d6

Exploratory result, captured 28 August 2026