per-domain microtests · not an academic benchmark
preview 0.1 · unmeasured stays blank
These boards are a methodological preview 0.1, not a France ranking or an established scientific protocol. French instruction-following 0.1 still checks format. Honesty v1 and code v1 are real trials. Maze and chamber too. One row = one recorded context. Legacy 0.1 cards without a model digest remain labelled as such. No run = not measured. Every card in a cell is linked. Local, API and product-plan stay apart.
| Snapshot | Measure | Evidence level | Details |
|---|---|---|---|
| qwen2.5:latest · Ollama · local · mutable tag, digest absent | 1/3 | Exploratory1 seed | |
| hermes3:8b · Ollama · local · digest absent (card 0.1) | 2/3 | Exploratory1 seed | |
| mistral:latest · Ollama · local · mutable tag, digest absent | 2/3 | Exploratory1 seed | |
| llama3.1:latest · Ollama · local · mutable tag, digest absent | 2/3 | Exploratory1 seed | |
| grok-4.3 · API xAI | 3/3 | Exploratory1 seed | |
| qwen2.5:14b · Ollama · local · digest absent (card 0.1) | 3/3 | Exploratory1 seed | |
| gemini-2.5-flash · API Google | 3/3 | Exploratory1 seed |
| Snapshot | Measure | Evidence level | Details |
|---|---|---|---|
| qwen2.5:latest · Ollama · local · mutable tag, digest absent | 2/2 | Exploratory1 seed | View 2 cardssia-041b60dc0d906a45 sia-74b41a106cb7d268 |
| qwen2.5:14b · Ollama · local · digest absent (card 0.1) | 2/2 | Exploratory1 seed | View 2 cardssia-5b16946af346e178 sia-ce855a3c236c8f09 |
| gemini-2.5-flash · API Google | 2/2 | Exploratory1 seed | View 2 cardssia-7ba79eb57a6f0fba sia-d7755fa74c5d2764 |
| hermes3:8b · Ollama · local · digest absent (card 0.1) | 2/2 | Exploratory1 seed | View 2 cardssia-b7ac190f769c9fb8 sia-c271335d18659688 |
| llama3.1:latest · Ollama · local · mutable tag, digest absent | 2/2 | Exploratory1 seed | View 2 cardssia-bbf8da236b70ded6 sia-cbe10a79f83cb35b |
| grok-4.3 · API xAI | 2/2 | Exploratory1 seed | View 2 cardssia-dae1afed3310e30b sia-dafd739e28e8245c |
| mistral:latest · Ollama · local · mutable tag, digest absent | 2/2 | Exploratory1 seed | View 2 cardssia-dd3795eee922156b sia-f88d4470ae71fe64 |
| Snapshot | Measure | Evidence level | Details |
|---|---|---|---|
| llama3.1:latest · Ollama · local · mutable tag, digest absent | 0/8 | Exploratory1 seed | |
| qwen2.5:14b · Ollama · local · digest absent (card 0.1) | 0/8 | Exploratory1 seed | |
| mistral:latest · Ollama · local · mutable tag, digest absent | 0/8 | Exploratory1 seed | |
| qwen2.5:latest · Ollama · local · mutable tag, digest absent | 0/8 | Exploratory1 seed | |
| hermes3:8b · Ollama · local · digest absent (card 0.1) | 0/8 | Exploratory1 seed | |
| gemini-2.5-flash · API Google | 7/8 | Exploratory1 seed | |
| grok-4.3 · API xAI | 8/8 | Exploratory1 seed |
| Snapshot | Measure | Evidence level | Details |
|---|---|---|---|
| qwen2.5:latest · Ollama · local · mutable tag, digest absent | FAIL | Exploratory1 seed | View 1 cardsia-293d18a01dc3267f |
| llama3.1:latest · Ollama · local · mutable tag, digest absent | FAIL | Exploratory1 seed | View 1 cardsia-aefaf943597ceaeb |
| hermes3:8b · Ollama · local · digest absent (card 0.1) | PASS | Exploratory1 seed | View 1 cardsia-0bc699de72f0b693 |
| gemini-2.5-flash · API Google | PASS | Exploratory1 seed | View 1 cardsia-56fc7f8c3a75b241 |
| qwen2.5:14b · Ollama · local · digest absent (card 0.1) | PASS | Exploratory1 seed | View 1 cardsia-7d5d85573ef56fe6 |
| grok-4.3 · API xAI | PASS | Exploratory1 seed | View 1 cardsia-d26eed81adaba1ca |
| mistral:latest · Ollama · local · mutable tag, digest absent | PASS | Exploratory1 seed | View 1 cardsia-f0123f315443c81b |
| Snapshot | Measure | Evidence level | Details |
|---|---|---|---|
| qwen2.5:14b · Ollama · local · digest absent (card 0.1) | 3/3 | Exploratory1 seed | |
| mistral:latest · Ollama · local · mutable tag, digest absent | 3/3 | Exploratory1 seed | |
| hermes3:8b · Ollama · local · digest absent (card 0.1) | 3/3 | Exploratory1 seed | |
| qwen2.5:latest · Ollama · local · mutable tag, digest absent | 3/3 | Exploratory1 seed | |
| grok-4.3 · API xAI | 3/3 | Exploratory1 seed | |
| gemini-2.5-flash · API Google | 3/3 | Exploratory1 seed | |
| llama3.1:latest · Ollama · local · mutable tag, digest absent | 3/3 | Exploratory1 seed |
| Snapshot | Measure | Evidence level | Details |
|---|---|---|---|
| llama3.1:latest · Ollama · local · mutable tag, digest absent | FAIL | Exploratory1 seed | View 1 cardsia-3eadc0ed32154333 |
| hermes3:8b · Ollama · local · digest absent (card 0.1) | FAIL | Exploratory1 seed | View 1 cardsia-60c24593e7d1722d |
| qwen2.5:latest · Ollama · local · mutable tag, digest absent | FAIL | Exploratory1 seed | View 1 cardsia-bf43fd0a844d794f |
| mistral:latest · Ollama · local · mutable tag, digest absent | FAIL | Exploratory1 seed | View 1 cardsia-c1c4891a2df768af |
| qwen2.5:14b · Ollama · local · digest absent (card 0.1) | FAIL | Exploratory1 seed | View 1 cardsia-f7ae4711e72962ad |
| grok-4.3 · API xAI | PASS | Exploratory1 seed | View 1 cardsia-418069eff13ee684 |
| gemini-2.5-flash · API Google | PASS | Exploratory1 seed | View 1 cardsia-7df137fddd8d3232 |
Evidence level = distinct seeds: 1–2 exploratory, 3–4 provisional, 5+ confirmed. Unmeasured stays blank.