Inference
EN

Gemini 4 Argon vs GPT-6.1 Terra

Change models
Gemini 4 ArgonGoogle
GPT-6.1 TerraOpenAI
IndexAll categories, out of 100.
78.5 ±4.3 best
77.1 ±3.8
GapIndex points below the top.
Top
−1.4 · no clear gap
CoverageIndex weight that has results.
80%
90% best
SpeedOutput tokens per second.
28/s
46/s best
EloLMArena rating and rank.
1530
—
ReleasedMonth of release.
2026-09
2026-10
Input / 1MUS dollars per 1M input tokens.
$2.00
$1.00 best
Output / 1MUS dollars per 1M output tokens.
$10.00
$5.00 best
Batch output / 1MBatch price per 1M output tokens.
$5.00
$2.50 best
1K chats2K tokens in, 500 out, each.
$9.00
$4.50 best
1K documents20K tokens in, 1K out, each.
$50.00
$25.00 best
1K agent tasks200K tokens in, 20K out, each.
$600.00
$300.00 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
77.3
78.6 best
CodingCode writing and repair.
76.7 best
74.4
ReasoningLogic problems and puzzles.
79.8
81.3 best
MultimodalTasks with images and text.
—
73.2
KnowledgeFacts and expert knowledge.
76.5 best
70.5
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
75.9
76.9 best

Benchmarks

34 shared
Only Gemini 4 Argon: 52Only GPT-6.1 Terra: 16
Gemini 4 Argon
GPT-6.1 Terra
Artificial Analysis Humanity's Last ExamKnowledge
57.1% best4 / 222
46.2%24 / 222
Artificial Analysis Long Context ReasoningReasoning
79.7%45 / 217
82.7% best23 / 217
GPQA diamond · Epoch AIKnowledge
96.4% best2 / 217
94.3%10 / 217
Critical Physics TasksReasoning
27.1%17 / 214
28.0% best16 / 214
OTIS Mock AIME 2024-2025Math
100.0%1 / 200
100.0%1 / 200
Artificial Analysis Omniscience AccuracyKnowledge
48.3% best26 / 164
47.6%28 / 164
Vibe Code Bench v1.1Coding
91.9% best3 / 123
84.0%19 / 123
Artificial Analysis SciCodeCoding
61.8% best5 / 114
55.1%28 / 114
SimpleQA VerifiedKnowledge
76.0% best3 / 91
57.3%21 / 91
FrontierMath-Tiers-1-3-v2-PrivateMath
86.0%13 / 90
90.9% best5 / 90
Legal Research BenchLegal
54.8% best5 / 90
26.0%62 / 90
Tax Agent BenchFinance
49.2% best4 / 82
17.1%58 / 82
LiveBench Data AnalysisReasoning
85.2% best1 / 80
82.3%4 / 80
LiveBench ReasoningReasoning
95.1% best1 / 80
88.7%20 / 80
Mystery Game PuzzlesReasoning
64.0%8 / 80
74.0% best4 / 80
FrontierMath-Tier-4-v2-PrivateMath
78.0%12 / 72
92.7% best6 / 72
Terminal-Bench 4.0Agentic
57.6% best8 / 61
49.5%11 / 61
Agent Arena steerabilityAgentic
13.29 / 54
16.6 best4 / 54
Agent Arena task outcomeAgentic
13.2 best7 / 54
9.711 / 54
LiveBench Coding 2.0Coding
89.7%15 / 52
90.8% best11 / 52