Gemini 3.7 Flash vs GPT-5.5

Change models
GPT-5.5OpenAI
IndexAll categories, out of 100.
68.5 ±2.2
69.1 ±2.5 best
GapIndex points below the top.
−0.6 · no clear gap
Top
CoverageIndex weight that has results.
100% best
95%
SpeedOutput tokens per second.
85/s best
52/s
EloLMArena rating and rank.
1489 best
1466
ReleasedMonth of release.
2026-08
2026-04
Input / 1MUS dollars per 1M input tokens.
$0.75 best
$5.00
Output / 1MUS dollars per 1M output tokens.
$3.75 best
$30.00
Batch output / 1MBatch price per 1M output tokens.
$1.88 best
$15.00
1K chats2K tokens in, 500 out, each.
$3.38 best
$25.00
1K documents20K tokens in, 1K out, each.
$18.75 best
$130.00
1K agent tasks200K tokens in, 20K out, each.
$225.00 best
$1,600.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
65.1
65.8 best
CodingCode writing and repair.
66.9 best
65.5
ReasoningLogic problems and puzzles.
68.7
74.1 best
MultimodalTasks with images and text.
67.7 best
66.8
KnowledgeFacts and expert knowledge.
71.2 best
70.4
MultilingualTasks in many languages.
72.3
—
InstructionTasks with strict prompt rules.
88.3 best
64.8
MathMath problems.
66.8
74.7 best

Benchmarks

62 shared
Only Gemini 3.7 Flash: 31Only GPT-5.5: 50
Gemini 3.7 Flash
GPT-5.5
47.9% best18 / 222
45.8%26 / 222
81.7%33 / 217
84.3% best7 / 217
94.8% best7 / 217
94.0%13 / 217
14.3%52 / 214
27.1% best17 / 214
97.2%34 / 200
100.0% best1 / 200
94.5% best4 / 199
93.5%8 / 199
55.3%12 / 164
58.0% best10 / 164
87.3% best6 / 149
86.5%13 / 149
TaxEval v2Finance
74.7%31 / 143
75.0% best25 / 143
88.7% best5 / 142
85.3%33 / 142
93.9% best5 / 135
93.2%10 / 135
MMLU ProKnowledge
90.1% best6 / 135
88.1%21 / 135
44.6% best40 / 133
42.5%44 / 133
84.6%14 / 131
85.0% best13 / 131
95.5% best17 / 126
95.0%19 / 126
70.4% best48 / 123
69.8%50 / 123
85.3%19 / 122
90.6% best14 / 122
96.6%24 / 116
97.5% best19 / 116
57.2% best21 / 114
55.8%27 / 114
85.5% best5 / 113
79.9%23 / 113