text model comparison
Grok 4.3 vs Mistral Large 4
Grok 4.3 and Mistral Large 4 are both current text models, from xAI and Mistral AI. Grok 4.3 is 8% cheaper per 1M input tokens than Mistral Large 4, $1.25 vs $1.36. On Arena Text, Grok 4.3 scores 1442 Elo and Mistral Large 4 1429 Elo (Arena, measured October 8, 2026). Both accept 1,000,000 tokens of context.
Data verified October 12, 2026 · Dataset 2026-10-12
Side by side
Standard-tier prices in effect today. The better value in each row is highlighted.
| Fact | Grok 4.3 | Mistral Large 4 |
|---|---|---|
| Price per 1M input tokens | $1.25 (better) | $1.36 |
| Price per 1M output tokens | $2.50 (better) | $4.18 |
| Cost of 10M input and 2M output tokens | $17.50 (better) | $21.96 |
| Arena Text | 1442 Elo (#33 of 39) (better) | 1429 Elo (#34 of 39) |
| SimpleQA Verified | 33.2% (#28 of 34) (better) | 20% (#32 of 34) |
| GPQA Diamond | 88.8% (#29 of 37) | Not measured |
| FrontierMath Tiers 1-3 (v2) | 42.8% (#32 of 37) | Not measured |
| Provider | xAI | Mistral AI |
| Release date | Not reported | October 6, 2026 |
| Access | API only | API only |
| Context window | 1,000,000 tokens | 1,000,000 tokens |
| Max output | Not reported | Not reported |
| Input | text, image | text, image |
| Output | text | text |
When to choose each
Grok 4.3
Best for
- General-purpose reasoning, instruction following, and agentic tool-use evaluations
Watch out for
- The published base rates double when requests reach the provider's 200,000-token long-context threshold
Mistral Large 4
Best for
- European data-residency workloads that want a frontier-scale multimodal model
- Teams planning to self-host once the open weights ship
Watch out for
- This is a public preview: Mistral says the reinforcement learning run is still in flight and the model will keep changing
- Weights and their licence were not published at the time of this update, so it is recorded as API-only
- Mistral offered a temporary 50% launch discount; the recorded rates are the list prices
- Epoch AI measured 20.0% on SimpleQA Verified, low for its size, so check factual recall on your own questions
Grok 4.3 vs Mistral Large 4 FAQ
Which is cheaper, Grok 4.3 or Mistral Large 4?
Grok 4.3 is 8% cheaper per 1M input tokens than Mistral Large 4, $1.25 vs $1.36. For 10M input and 2M output tokens, Grok 4.3 costs $17.50 and Mistral Large 4 $21.96 at standard rates.
Which scores higher on independent benchmarks, Grok 4.3 or Mistral Large 4?
Grok 4.3 leads on Arena Text, 1442 Elo to 1429 Elo; Grok 4.3 leads on SimpleQA Verified, 33.2% to 20%. Scores are independent evaluations, not either vendor's launch figures.
Which has the larger context window, Grok 4.3 or Mistral Large 4?
Both accept 1,000,000 tokens of context.
Related comparisons
Production evaluation
Choosing between Grok 4.3 and Mistral Large 4?
Public benchmarks narrow the shortlist. We run both on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- A head-to-head evaluation on your real workload
- Routing between models by cost and difficulty