Codestral 25.01 vs Grok 4.6 benchmark

Side-by-Side Benchmark Matrix

Recommended Workload Routing

Frequently Asked Questions

Which is better overall, Codestral 25.01 or Grok 4.6?

Grok 4.6 has the higher preference Elo in our latest snapshot (1,592). “Better” still depends on coding, price, and latency — see the table.

Which is better at coding, Codestral 25.01 or Grok 4.6?

Grok 4.6 leads SWE-bench at 69.1% vs 51.8%. SWE-bench is one harness, not your repo.

Which is cheaper to run in production?

Codestral 25.01 output tokens are $0.9/1M versus $6/1M. Input prices and retry rates still move the real bill.

Which is faster, Codestral 25.01 or Grok 4.6?

Codestral 25.01 has the lower time-to-first-token (150 ms vs 195 ms). Tokens/sec is a separate column if you care about long completions.

Which has the larger context window?

Grok 4.6 accepts 500k tokens versus 256k.

Can I self-host either model?

Neither model is marked open-weights here. You are comparing hosted APIs.

Are these scores from CompareLLM’s own evals?

No. V1 aggregates public leaderboards (and optional first-party latency pings). Each cell names its source and date. Read /methodology.

What does preference Elo mean on this page?

Preference Elo is a crowd vote from LMArena / Arena. People see two hidden answers and pick the one they like more. The model that wins more often gets a higher Elo. That means people preferred it — not that it passed a school test. It is not SWE-bench, not accuracy, and not a number we invent. Codestral 25.01 and Grok 4.6 Elo cells are dated snapshots from the named source — we do not compute Arena ourselves.