Mistral Medium 3.5 128B vs Nemotron 3.5 Super VL 120B A12B NVFP4

Change models
IndexAll categories, out of 100.
50.2 ±6.0
50.7 ±5.3 best
GapIndex points below the top.
−0.5 · no clear gap
Top
CoverageIndex weight that has results.
85%
85%
SpeedOutput tokens per second.
—
—
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-04
2026-10
Input / 1MUS dollars per 1M input tokens.
$1.50
—
Output / 1MUS dollars per 1M output tokens.
$7.50
—
1K chats2K tokens in, 500 out, each.
$6.75
—
1K documents20K tokens in, 1K out, each.
$37.50
—
1K agent tasks200K tokens in, 20K out, each.
$450.00
—
ContextMaximum tokens in one request.
256K
1M best
AgenticMulti-step tasks with tools.
59.9 best
45.0
CodingCode writing and repair.
53.3
55.0 best
ReasoningLogic problems and puzzles.
45.8
55.5 best
MultimodalTasks with images and text.
39.6
47.0 best
KnowledgeFacts and expert knowledge.
41.2
52.6 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
53.3
55.8 best
MathMath problems.
—
—

Benchmarks

8 shared
Only Mistral Medium 3.5 128B: 5Only Nemotron 3.5 Super VL 120B A12B NVFP4: 15
Mistral Medium 3.5 128B
Nemotron 3.5 Super VL 120B A12B NVFP4
13.8%130 / 222
30.7% best74 / 222
69.3% best115 / 217
67.7%127 / 217
0.0%150 / 214
10.6% best63 / 214
23.0%117 / 165
25.9% best101 / 165
13.0%91 / 133
33.1% best55 / 133
40.2%87 / 114
47.8% best61 / 114
77.6% best33 / 114
71.1%64 / 114
91.4% best2 / 32
17.8%27 / 32