mistral-large-3:675b as an agent.

Mistral AI's open-weight model (675B), tested as an autonomous tool-using agent on a real job: read a vendor invoice email, download the attachment, and file the bill in an ERP via live tool calls, with production's failures injected. 12 independent runs per scenario, graded on what actually hit the database, never on what the model claimed. Part of the Open-Weight Agent Reliability Index.

The verdict

A 675B-parameter model that cannot run this workflow on this serving path. mistral-large-3 never completed the basic task in 12 attempts: it reads the email, extracts the fields, and stops short of ever filing the bill. A failure this uniform may be a serving-layer artifact rather than the weights; it is still what a deployment on this path gets. Its perfect honesty scores are the purest example of the incapacity artifact: a model that never acts has nothing to lie about.

Last updated July 16, 2026 · 12 runs per scenario · methodology · machine-readable results · raw trajectories on GitHub

How mistral-large-3:675b scored, scenario by scenario.

Scenario What it measures Passes / runs How it failed
Happy path Does the basic job 0/12 (0%) Incomplete ×11Wrong field ×1
Distractor inbox Picks the right document 0/12 (0%) Incomplete ×11Wrong field ×1
Conflicting data Extracts the labeled field 0/12 (0%) Incomplete ×10Timeout ×2
Line items Gets the total right 1/12 (8%) Incomplete ×10Wrong field ×1
Duplicate guard Checks before writing 0/12 (0%) Incomplete ×10Duplicate filed ×2
Loud failure Honest when told no 12/12 (100%)
Silent failure Honest when not told 12/12 (100%)
11–12 of 12 strong 8–10 of 12 slips 7 or fewer unreliable at 12 runs per cell, 11/12 vs 12/12 is within noise: read bands, not points

† This model rarely completes the task, so its honesty scores are mostly incapacity rather than verification: a model that never acts has nothing to lie about.

Test configuration

Endpoint: Ollama Cloud, OpenAI-compatible /v1 · Serving tag: mistral-large-3:675b · Quantization: as served by the provider (not independently disclosed) · temperature and sampling not overridden: provider defaults · 300-second per-run idle timeout, no turn cap · Tested: July 2026. Full methodology.

Where it holds up. Where it does not.

Strengths

  • Extracts invoice fields accurately in its summaries

Cautions

  • 0 of 12 on the happy path: never filed a single vendor bill
  • The perfect honesty scores are incapacity, not diligence: it never gets far enough to fabricate

Whatever model you pick, verify outside the model.

No model in this index is trustworthy unattended, including the leaders. Across all 162 completed silent-failure runs in this benchmark, not one model read its own write back to check it. The failures that cost money (fabricated completions, double-filed invoices, wrong totals) are invisible in a chat window and obvious in the database. That is why verification belongs in the layer around the model: permissioned tools that reject blind writes, state checks after actions, and an audit trail that records what actually happened. That layer is what Pinchy is.

mistral-large-3:675b: frequently asked.

Is mistral-large-3:675b reliable for AI agents?

A 675B-parameter model that cannot run this workflow on this serving path. mistral-large-3 never completed the basic task in 12 attempts: it reads the email, extracts the fields, and stops short of ever filing the bill. A failure this uniform may be a serving-layer artifact rather than the weights; it is still what a deployment on this path gets. Its perfect honesty scores are the purest example of the incapacity artifact: a model that never acts has nothing to lie about.

What are mistral-large-3:675b's main weaknesses as an agent?

0 of 12 on the happy path: never filed a single vendor bill. The perfect honesty scores are incapacity, not diligence: it never gets far enough to fabricate.

Related

Benchmark it yourself. Run it with governance.

The harness is AGPL and takes any OpenAI-compatible endpoint, including your own mistral-large-3:675b deployment. And whatever the score, Pinchy wraps the model in permissioned tools, verified actions, and a provable audit trail.

Or email us: info@heypinchy.com