Inference
EN

Gemini 4 Carbon vs GPT-6.1 Terra

Change models
Gemini 4 CarbonGoogle
GPT-6.1 TerraOpenAI
IndexAll categories, out of 100.
82.7 ±5.1 best
77.1 ±3.8
GapIndex points below the top.
Top
−5.6 · no clear gap
CoverageIndex weight that has results.
80%
90% best
SpeedOutput tokens per second.
31/s
46/s best
EloLMArena rating and rank.
1538
—
ReleasedMonth of release.
2026-10
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.
83.2 best
78.6
CodingCode writing and repair.
80.5 best
74.4
ReasoningLogic problems and puzzles.
83.9 best
81.3
MultimodalTasks with images and text.
—
73.2
KnowledgeFacts and expert knowledge.
79.5 best
70.5
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
77.2 best
76.9

Benchmarks

22 shared
Only Gemini 4 Carbon: 17Only GPT-6.1 Terra: 28
Gemini 4 Carbon
GPT-6.1 Terra
Artificial Analysis Long Context ReasoningReasoning
79.3%52 / 217
82.7% best23 / 217
GPQA diamond · Epoch AIKnowledge
96.5% best1 / 217
94.3%10 / 217
OTIS Mock AIME 2024-2025Math
100.0%1 / 200
100.0%1 / 200
Artificial Analysis Omniscience AccuracyKnowledge
58.3% best9 / 164
47.6%28 / 164
Vibe Code Bench v1.1Coding
89.1% best9 / 123
84.0%19 / 123
SimpleQA VerifiedKnowledge
77.7% best2 / 91
57.3%21 / 91
FrontierMath-Tiers-1-3-v2-PrivateMath
90.5%6 / 90
90.9% best5 / 90
Legal Research BenchLegal
55.8% best1 / 90
26.0%62 / 90
Tax Agent BenchFinance
51.8% best1 / 82
17.1%58 / 82
Mystery Game PuzzlesReasoning
73.0%5 / 80
74.0% best4 / 80
FrontierMath-Tier-4-v2-PrivateMath
95.1% best4 / 72
92.7%6 / 72
Terminal-Bench 4.0Agentic
63.1% best4 / 61
49.5%11 / 61
Agent Arena steerabilityAgentic
19.1 best2 / 54
16.64 / 54
Agent Arena task outcomeAgentic
18.4 best4 / 54
9.711 / 54
Furniture AssemblyReasoning
77.5%6 / 37
79.2% best5 / 37
HLAB-Vals-1.1Legal
17.5% best8 / 35
1.7%35 / 35
EBR-benchReasoning
87.6% best2 / 31
78.1%3 / 31
Artificial Analysis AutomationBenchAgentic
77.8% best1 / 23
60.2%12 / 23
Artificial Analysis GDP.pdfAgentic
28.4%7 / 22
28.6% best6 / 22
Artificial Analysis Terminal-Bench v4.0Agentic
65.2% best2 / 22
55.6%9 / 22