ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

GLM-4.5-AirvsMistral Medium 3.5

Mistral Medium 3.5 leads 1 of 1 shared benchmark. GLM-4.5-Air is 6.9x cheaper per token. Mistral Medium 3.5 has the larger context window (256K tokens).

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
0 – 1
Mistral Medium 3.5 leads
Cheaper per token
GLM-4.5-Air
6.9x cheaper, input + output
Larger context
Mistral Medium 3.5
256K tokens
Provider uptime (30d)
— · 100%
Z.ai · Mistral AI
text
Context
128K
Max out
98K
Input /1M
$0.2
Output /1M
$1.1
Cached /1M
$0.03
Scores
2 · 2 core
Mistral Medium 3.5
Mistral AI · released 2026-04-28
textvision
Context
256K
Max out
Input /1M
$1.5
Output /1M
$7.5
Cached /1M
$0.15
Scores
3 · 2 core
Quality

Benchmark matrix

BenchmarkGLM-4.5-AirMistral Medium 3.5ΔEdge
Reported by both · 1
LMArena Elo1383.6 1420.6 -37Mistral Medium 3.5
Only GLM-4.5-Air reports · 1
AIME 202583.3% matharenanot reported
Only Mistral Medium 3.5 reports · 2
SWE-bench Verifiednot reported77.6%
Tau3 Telecomnot reported91.4
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 GLM-4.5-Air minus Mistral Medium 3.5 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

SpecGLM-4.5-AirMistral Medium 3.5Edge
Context window128K tokens256K tokensMistral Medium 3.5
Max output98K tokens
Input price / 1M$0.2 $1.5 GLM-4.5-Air
Output price / 1M$1.1 $7.5 GLM-4.5-Air
Cached input / 1M$0.03 $0.15 GLM-4.5-Air
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$1.3$9GLM-4.5-Air
Modalitiestexttext · visionMistral Medium 3.5
Released2026-04-28
Cited benchmark scores23
Reliability

Provider status

All providers
More matchups

Mistral Medium 3.5 vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run GLM-4.5-Air and Mistral Medium 3.5 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.