Gemini 2.5 Flash vs Mistral Large 3

Change models
IndexAll categories, out of 100.
35.1 ±5.0 best
34.4 ±4.4
GapIndex points below the top.
Top
−0.7 · no clear gap
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
107/s best
65/s
EloLMArena rating and rank.
1417
1429 best
ReleasedMonth of release.
2025-06
2025-12
Input / 1MUS dollars per 1M input tokens.
$0.30 best
$0.50
Output / 1MUS dollars per 1M output tokens.
$2.50
$1.50 best
Batch output / 1MBatch price per 1M output tokens.
$1.25
—
1K chats2K tokens in, 500 out, each.
$1.85
$1.75 best
1K documents20K tokens in, 1K out, each.
$8.50 best
$11.50
1K agent tasks200K tokens in, 20K out, each.
$110.00 best
$130.00
ContextMaximum tokens in one request.
1.05M best
262K
AgenticMulti-step tasks with tools.
14.1
30.0 best
CodingCode writing and repair.
32.0
38.0 best
ReasoningLogic problems and puzzles.
40.3 best
34.4
MultimodalTasks with images and text.
40.2 best
34.4
KnowledgeFacts and expert knowledge.
37.8
39.1 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
26.0 best
23.5
MathMath problems.
43.8 best
34.0

Benchmarks

9 shared
Only Gemini 2.5 Flash: 7Only Mistral Large 3: 18
Gemini 2.5 Flash
Mistral Large 3
4.7% best177 / 216
4.2%188 / 216
49.9% best150 / 211
36.0%168 / 211
1.4% best108 / 207
0.0%145 / 207
68.3% best129 / 193
68.0%131 / 193
26.1% best99 / 170
25.0%106 / 170
14.9%134 / 143
24.6% best116 / 143
39.0% best102 / 140
36.2%114 / 140
65.5% best77 / 109
55.7%91 / 109
IOI v1Coding
2.6%54 / 61
4.0% best49 / 61