Gemini 3.7 Flash vs Gemini 4 Carbon

Change models
IndexAll categories, out of 100.
68.5 ±2.2
82.7 ±5.1 best
GapIndex points below the top.
−14.2
Top
CoverageIndex weight that has results.
100% best
80%
SpeedOutput tokens per second.
85/s best
31/s
EloLMArena rating and rank.
1489
1538 best
ReleasedMonth of release.
2026-08
2026-10
Input / 1MUS dollars per 1M input tokens.
$0.75 best
$2.00
Output / 1MUS dollars per 1M output tokens.
$3.75 best
$10.00
Batch output / 1MBatch price per 1M output tokens.
$1.88 best
$5.00
1K chats2K tokens in, 500 out, each.
$3.38 best
$9.00
1K documents20K tokens in, 1K out, each.
$18.75 best
$50.00
1K agent tasks200K tokens in, 20K out, each.
$225.00 best
$600.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
65.1
83.2 best
CodingCode writing and repair.
66.9
80.5 best
ReasoningLogic problems and puzzles.
68.7
83.9 best
MultimodalTasks with images and text.
67.7
—
KnowledgeFacts and expert knowledge.
71.2
79.5 best
MultilingualTasks in many languages.
72.3
—
InstructionTasks with strict prompt rules.
88.3
—
MathMath problems.
66.8
77.2 best

Benchmarks

22 shared
Only Gemini 3.7 Flash: 71Only Gemini 4 Carbon: 17
Gemini 3.7 Flash
Gemini 4 Carbon
81.7% best33 / 217
79.3%52 / 217
94.8%7 / 217
96.5% best1 / 217
97.2%34 / 200
100.0% best1 / 200
55.3%12 / 164
58.3% best9 / 164
84.6%14 / 131
92.1% best5 / 131
95.5%17 / 126
97.5% best5 / 126
70.4%48 / 123
89.1% best9 / 123
85.3%19 / 122
97.9% best3 / 122
96.6%24 / 116
98.5% best6 / 116
69.2%12 / 91
77.7% best2 / 91
Chess PuzzlesReasoning
66.0%6 / 90
78.0% best2 / 90
71.6%28 / 90
90.5% best6 / 90
34.6%49 / 90
55.8% best1 / 90
22.8%48 / 82
51.8% best1 / 82
37.0%20 / 80
73.0% best5 / 80
36.6%29 / 72
95.1% best4 / 72
12.1%42 / 61
63.1% best4 / 61
−7.342 / 54
19.1 best2 / 54
−3.538 / 54
18.4 best4 / 54
26.7%30 / 37
77.5% best6 / 37