Inference
EN

Gemini 3.8 Flash vs GPT-6 Sol

Change models
Gemini 3.8 FlashGoogle
GPT-6 SolOpenAI
IndexAll categories, out of 100.
67.8 ±2.5
72.8 ±2.2 best
GapIndex points below the top.
−5.0
Top
CoverageIndex weight that has results.
95%
100% best
SpeedOutput tokens per second.
68/s best
61/s
EloLMArena rating and rank.
1500 best
1397
ReleasedMonth of release.
2026-09
2026-09
Input / 1MUS dollars per 1M input tokens.
$0.825 best
$2.00
Output / 1MUS dollars per 1M output tokens.
$4.13 best
$10.00
Batch output / 1MBatch price per 1M output tokens.
$1.88 best
$5.00
1K chats2K tokens in, 500 out, each.
$3.71 best
$9.00
1K documents20K tokens in, 1K out, each.
$20.63 best
$50.00
1K agent tasks200K tokens in, 20K out, each.
$247.50 best
$600.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
65.3
68.6 best
CodingCode writing and repair.
66.2
73.9 best
ReasoningLogic problems and puzzles.
68.3
76.1 best
MultimodalTasks with images and text.
67.1
70.1 best
KnowledgeFacts and expert knowledge.
70.9
71.9 best
MultilingualTasks in many languages.
—
65.5
InstructionTasks with strict prompt rules.
91.3 best
65.3
MathMath problems.
64.3
75.8 best

Benchmarks

71 shared
Only Gemini 3.8 Flash: 35Only GPT-6 Sol: 23
Gemini 3.8 Flash
GPT-6 Sol
Artificial Analysis Humanity's Last ExamKnowledge
47.8%20 / 222
47.9% best18 / 222
Artificial Analysis Long Context ReasoningReasoning
81.3%34 / 217
83.7% best10 / 217
GPQA diamond · Epoch AIKnowledge
95.4% best5 / 217
94.3%10 / 217
Critical Physics TasksReasoning
18.3%34 / 214
30.9% best8 / 214
OTIS Mock AIME 2024-2025Math
98.9%22 / 200
100.0% best1 / 200
Artificial Analysis Omniscience AccuracyKnowledge
50.5%19 / 164
54.5% best13 / 164
GDPval-AA normalizedAgentic
46.8%34 / 133
50.4% best27 / 133
ARC-AGI-2 (semi-private)Reasoning
89.2%11 / 131
89.6% best10 / 131
ARC-AGI-1 (semi-private)Reasoning
98.5% best1 / 126
95.5%17 / 126
Vibe Code Bench v1.1Coding
78.7%34 / 123
87.8% best12 / 123
ARC-AGI-2 (public eval)Reasoning
92.5% best11 / 122
90.0%17 / 122
ARC-AGI-1 (public eval)Reasoning
98.0% best11 / 116
97.8%14 / 116
Artificial Analysis SciCodeCoding
56.6%23 / 114
57.6% best18 / 114
Artificial Analysis MMMU-ProMultimodal
85.6% best4 / 113
82.9%12 / 113
MedScribeHealthcare
84.5% best34 / 109
82.0%52 / 109
MedCodeHealthcare
48.1% best31 / 106
47.1%36 / 106
SimpleQA VerifiedKnowledge
69.7% best10 / 91
60.7%17 / 91
Chess PuzzlesReasoning
58.0% best14 / 90
56.0%15 / 90
FrontierMath-Tiers-1-3-v2-PrivateMath
68.4%32 / 90
89.8% best8 / 90
Legal Research BenchLegal
38.9% best38 / 90
28.8%57 / 90