← Benches
gate.fidelity.enum
GategauntletA deterministic gate probe — harness-invariant vitals / fidelity / tool-use check that every model must clear before the ladders count.
Solved
21/23
runs passed
Models
22
have attempted
Harnesses
2
scaffolds tried
Runs (latest per model × harness — solved sorted first)
| Model | Harness | Result | Turns | tok/s | Latency | Ctx | When |
|---|---|---|---|---|---|---|---|
| gpt-oss-120b | baseline | PASS | 1 | 34.2 | 497ms | 64k | 2026-06-23 |
| granite-4.1-8b | baseline | PASS | 1 | 14.4 | 139ms | 64k | 2026-06-23 |
| llama-3.3-70b | baseline | PASS | 1 | 2.7 | 741ms | 64k | 2026-06-23 |
| devstral-small-2-2512 | baseline | PASS | 1 | 7.5 | 268ms | 64k | 2026-06-23 |
| mistral-small-3.1-24b-instruct-2503 | baseline | PASS | 1 | 7.6 | 262ms | 64k | 2026-06-23 |
| qwen3.5-122b-a10b-cluster | baseline | PASS | 1 | 16.8 | 19.7s | 64k | 2026-06-29 |
| qwen3.5-4b | baseline | PASS | 1 | 45.4 | 7.3s | 128k | 2026-06-30 |
| gpt-oss-20b | baseline | PASS | 1 | 73.9 | 988ms | 64k | 2026-07-01 |
| qwen3-coder-30b | baseline | PASS | 1 | 17.2 | 116ms | 64k | 2026-07-01 |
| gemma-4-26b-a4b-it | baseline | PASS | 1 | 6.8 | 294ms | 64k | 2026-07-01 |
| qwen3.6-35b-a3b-or | baseline | PASS | 1 | 89.7 | 3.0s | 64k | 2026-07-01 |
| gemini-2.5-flash-lite | baseline | PASS | 1 | 0.9 | 1.2s | 64k | 2026-07-01 |
| qwen3.5-0.8b | baseline | PASS | 1 | 23.0 | 87ms | 64k | 2026-07-01 |
| qwen3.6-27b | baseline | PASS | 1 | 7.9 | 30.1s | 64k | 2026-07-01 |
| qwen3.6-35b-bf16 | baseline | PASS | 1 | 34.2 | 7.7s | 64k | 2026-07-02 |
| qwen3.5-2b | baseline | PASS | 1 | 27.0 | 74ms | 64k | 2026-07-02 |
| granite-4.1-30b | baseline | PASS | 1 | 6.4 | 313ms | 64k | 2026-07-02 |
| qwen3.6-27b | v1.7.1 | PASS | 1 | 6.9 | 434ms | 64k | 2026-07-02 |
| qwen3.6-35b-a3b | baseline | PASS | 1 | 25.2 | 119ms | 64k | 2026-07-02 |
| qwen3-next-80b | baseline | PASS | 1 | 17.7 | 113ms | 64k | 2026-07-02 |
| claude-sonnet-4.6 | baseline | PASS | 1 | 2.5 | 1.6s | 195k | 2026-07-06 |
| deepseek-r1-distill-qwen-32b | baseline | fail | 1 | 4.6 | 1.5m | 64k | 2026-07-02 |
| phi-4-reasoning-plus | baseline | fail | 1 | 14.4 | 23.6s | 64k | 2026-07-02 |
Transcripts
gpt-oss-120b · baseline · PASS
done
granite-4.1-8b · baseline · PASS
done
llama-3.3-70b · baseline · PASS
done
devstral-small-2-2512 · baseline · PASS
done
mistral-small-3.1-24b-instruct-2503 · baseline · PASS
done
qwen3.5-122b-a10b-cluster · baseline · PASS
done
qwen3.5-4b · baseline · PASS
done
gpt-oss-20b · baseline · PASS
done
qwen3-coder-30b · baseline · PASS
done
gemma-4-26b-a4b-it · baseline · PASS
done
qwen3.6-35b-a3b-or · baseline · PASS
done
gemini-2.5-flash-lite · baseline · PASS
done
qwen3.5-0.8b · baseline · PASS
done
qwen3.6-27b · baseline · PASS
done
qwen3.6-35b-bf16 · baseline · PASS
done
qwen3.5-2b · baseline · PASS
done
granite-4.1-30b · baseline · PASS
done
qwen3.6-27b · v1.7.1 · PASS
done
qwen3.6-35b-a3b · baseline · PASS
done
qwen3-next-80b · baseline · PASS
done
claude-sonnet-4.6 · baseline · PASS
done
deepseek-r1-distill-qwen-32b · baseline · fail
The correct status for a task that has been completed and merged is: **done**
phi-4-reasoning-plus · baseline · fail
User says: "A task's work has been completed and merged. Reply with the single status value that means finished. Choose exactly one from this list: todo, backlog, in_progress, in_review, done, blocked, cancelled. Output only that one value in lowercase, nothing else." So answer is "done". But check instructions: "A task's work has been completed and merged" implies that the correct status is "done", because it means finished. Wait, but careful reading: The list provided: todo, backlog, in_progress, in_review, done, blocked, cancelled. Which one means finished? "Done" means finished. But check instructions: "A task's work has been completed and merged." That implies that the status is "done". So answer should be "done". But wait, maybe it's "in_review"? No, because "merged" means code review passed. But then "done" is the final state. Wait, but careful reading: "A task's work has been completed and merged." The instructions say: "Reply with the single status value that means finished." So answer is "done". But check list: "todo", "backlog", "in_progress", "in_review", "done", "blocked", "cancelled". Which one means finished? "Done" means finished. So answer is "done". I must output exactly "done" in lowercase, nothing else. Thus answer: done I'll produce final answer as "done". We'll check instructions: "Output only that one value in lowercase, nothing else." So I'll output "done" with no extra text. I'll now produce answer.done