Gemini 3 Flash vs GPT-5.1

Change models
GPT-5.1OpenAI
IndexAll categories, out of 100.
55.2 ±3.9 best
55.0 ±3.7
GapIndex points below the top.
Top
−0.2 · no clear gap
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
198/s best
47/s
EloLMArena rating and rank.
1466 best
1422
ReleasedMonth of release.
2025-12
2025-11
Input / 1MUS dollars per 1M input tokens.
$0.50 best
$1.25
Output / 1MUS dollars per 1M output tokens.
$3.00 best
$10.00
Batch output / 1MBatch price per 1M output tokens.
—
$5.00
1K chats2K tokens in, 500 out, each.
$2.50 best
$7.50
1K documents20K tokens in, 1K out, each.
$13.00 best
$35.00
1K agent tasks200K tokens in, 20K out, each.
$160.00 best
$450.00
ContextMaximum tokens in one request.
1M best
400K
AgenticMulti-step tasks with tools.
48.3
52.2 best
CodingCode writing and repair.
56.7 best
53.2
ReasoningLogic problems and puzzles.
50.6
56.1 best
MultimodalTasks with images and text.
67.5 best
58.2
KnowledgeFacts and expert knowledge.
60.5 best
57.0
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
40.5
57.0 best
MathMath problems.
57.0
57.2 best

Benchmarks

18 shared
Only Gemini 3 Flash: 14Only GPT-5.1: 26
Gemini 3 Flash
GPT-5.1
15.0%127 / 222
28.5% best87 / 222
55.3%147 / 217
80.0% best43 / 217
89.4% best48 / 217
87.6%62 / 217
1.4%113 / 214
4.9% best84 / 214
95.6% best40 / 200
88.6%67 / 200
81.2%95 / 199
87.3% best58 / 199
45.8% best35 / 167
37.7%64 / 167
43.3%103 / 149
81.9% best66 / 149
55.1%72 / 146
72.9% best33 / 146
78.6% best32 / 113
75.5%48 / 113
66.8% best13 / 91
48.0%35 / 91
Chess PuzzlesReasoning
40.0%36 / 90
42.0% best33 / 90
20.0% best45 / 80
16.0%56 / 80
35.6% best14 / 69
31.0%18 / 69
4.2%26 / 55
12.5% best17 / 55
56.6% best16 / 52
41.2%35 / 52
75.4% best13 / 32
66.9%25 / 32
92.7%
90.6%