Gemini 3 Flash vs GPT-5

Change models
GPT-5OpenAI
IndexAll categories, out of 100.
55.0 ±4.0
55.0 ±4.2
GapIndex points below the top.
Top
Top
CoverageIndex weight that has results.
95% best
90%
SpeedOutput tokens per second.
198/s best
76/s
EloLMArena rating and rank.
1466 best
1406
ReleasedMonth of release.
2025-12
2025-08
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.
48.5
53.1 best
CodingCode writing and repair.
56.8 best
52.5
ReasoningLogic problems and puzzles.
50.8
55.4 best
MultimodalTasks with images and text.
67.3 best
61.2
KnowledgeFacts and expert knowledge.
60.7 best
58.4
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
40.5
—
MathMath problems.
57.3 best
55.3

Benchmarks

15 shared
Only Gemini 3 Flash: 16Only GPT-5: 30
Gemini 3 Flash
GPT-5
89.4% best47 / 217
86.2%68 / 217
95.6% best40 / 200
91.4%56 / 200
66.8% best13 / 91
50.1%30 / 91
Chess PuzzlesReasoning
40.0% best36 / 90
36.0%42 / 90
51.2%54 / 90
55.4% best51 / 90
20.0%45 / 80
23.0% best39 / 80
17.1%52 / 72
22.0% best48 / 72
35.6% best14 / 69
32.4%16 / 69
60.0%11 / 64
60.0%11 / 64
4.2%26 / 55
12.5% best17 / 55
0.0%3 / 36
0.0%3 / 36
75.4% best13 / 32
73.6%19 / 32
76.8%14 / 23
81.6% best6 / 23
82.5% best3 / 22
62.5%12 / 22
91.2%8 / 18
95.8% best5 / 18