Compare / head-to-head
CodestralvsGrok 4.6
Codestral and Grok 4.6 do not yet share a public benchmark, so quality cannot be compared apples-to-apples. Codestral is 6.7x cheaper per token. Grok 4.6 has the larger context window (500K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0
no overlap yet
Cheaper per token
Codestral
6.7x cheaper, input + output
Larger context
Grok 4.6
500K tokens
Provider uptime (30d)
100% · —
Mistral AI · xAI
Codestral
Mistral AI · released 2025-01-13
text
Quality
Benchmark matrix
0 shared · 1 only Codestral · 15 only Grok 4.6| Benchmark | Codestral | Grok 4.6 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 0 | ||||
| No public benchmark is reported for both models yet. | ||||
| Only Codestral reports · 1 | ||||
| HumanEval | 86.6% ↗ | not reported | — | — |
| Only Grok 4.6 reports · 15 | ||||
| GPQA Diamond | not reported | 94% ↗epoch | — | — |
| AA-Briefcase | not reported | 1577 ↗ | — | — |
| APEX-Agents | not reported | 57.5% ↗ | — | — |
| APEX-SWE | not reported | 56.4% ↗ | — | — |
| Artificial Analysis Intelligence Index | not reported | 61 ↗ | — | — |
| CursorBench 3.2 | not reported | 69.9% ↗ | — | — |
| DeepSWE v1.1 | not reported | 65.9% ↗ | — | — |
| FrontierCode v1.1 (Extended) | not reported | 61.3% ↗ | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | not reported | 31.7% ↗epoch | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | not reported | 66% ↗epoch | — | — |
| GDPVal-AA v2 | not reported | 1753 ↗ | — | — |
| Harvey LAB (Vals) | not reported | 15.8% ↗ | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | not reported | 99.2% ↗epoch | — | — |
| SimpleQA Verified | not reported | 49.3% ↗epoch | — | — |
| Terminal-Bench 3.0 | not reported | 26% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Codestral minus Grok 4.6 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Codestral | Grok 4.6 | Edge |
|---|---|---|---|
| Context window | 256K tokens | 500K tokens | Grok 4.6 |
| Max output | — | — | — |
| Input price / 1M | $0.3 ↗ | $2 ↗ | Codestral |
| Output price / 1M | $0.9 ↗ | $6 ↗ | Codestral |
| Cached input / 1M | $0.03 ↗ | $0.5 ↗ | Codestral |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $1.2 | $8 | Codestral |
| Modalities | text | text · vision | Grok 4.6 |
| Released | 2025-01-13 | 2026-08-12 | — |
| Cited benchmark scores | 1 | 15 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Codestral vs …
Models sharing the most benchmarksMore matchups
Grok 4.6 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Codestral and Grok 4.6 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.