Celeris-1 vs Magistral Medium
Change modelsCeleris-1Celeris
Magistral MediumMistral
IndexAll categories, out of 100.
33.7 ±8.2
33.7 ±4.1
GapIndex points below the top.
Top
Top
CoverageIndex weight that has results.
75%
95% best
SpeedOutput tokens per second.
1,555/s
—
EloLMArena rating and rank.
—
1255
ReleasedMonth of release.
2026-07
2025-06
Input / 1MUS dollars per 1M input tokens.
$0.20
—
Output / 1MUS dollars per 1M output tokens.
$0.70
—
1K chats2K tokens in, 500 out, each.
$0.75
—
1K documents20K tokens in, 1K out, each.
$4.70
—
1K agent tasks200K tokens in, 20K out, each.
$54.00
—
ContextMaximum tokens in one request.
128K best
40K
AgenticMulti-step tasks with tools.
34.0 best
30.6
CodingCode writing and repair.
24.0
39.2 best
ReasoningLogic problems and puzzles.
35.1 best
28.4
MultimodalTasks with images and text.
—
39.2
KnowledgeFacts and expert knowledge.
35.5 best
35.2
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
25.9 best
12.5
MathMath problems.
—
41.8
Benchmarks
4 sharedOnly Celeris-1: 6Only Magistral Medium: 27
Celeris-1
Magistral Medium