GLM-5.2 vs Mistral Large 3
Head-to-head technical comparison of intelligence, capabilities, and API pricing.
Which should you use?
GLM-5.2 leads on the composite index by 2.3 points (91.5 vs 89.2).
Cost is the sharper difference: GLM-5.2 is 2.8x the input price of Mistral Large 3 ($1.4 against $0.5 per 1M), so at volume the choice is usually decided by budget rather than benchmarks.
Only GLM-5.2 ships open weights, which decides it outright if the workload has to run on your own hardware.
Pick GLM-5.2 when
- Higher composite index — 91.5 against 89.2, a gap of 2.3 points.
- Ahead on Arena Elo by 35 points (1465 vs 1430), which is outside the board's published confidence intervals.
- Stronger on MMLU-Pro: 91.2% against 89.2%.
- Open weights, so it is the only one of the two you can run on your own hardware or keep data entirely in-house.
Pick Mistral Large 3 when
- Cheaper input tokens — $0.5 against $1.4 per 1M, so GLM-5.2 costs 2.8x as much to feed.
- Better value per point of measured capability: $0.006 per index point against $0.015.
Value per point of measured capability, at list input pricing: Mistral Large 3 $0.006 · GLM-5.2 $0.015 per index point. Run your own token mix through the token cost calculator — a comparison at list price ignores caching and batch discounts, which move real bills more than this gap does.
Where these numbers come from
Figures as of 2026-09-14. Arena Elo and pricing are read from the public board and each vendor's own pricing page; see the full leaderboard for all 34 models and which columns are measured rather than estimated, or the benchmark matrix for scores benchmark by benchmark.