Inference
EN

Claude Opus 5 vs GPT-6.1 Terra

Change models
Claude Opus 5Anthropic
GPT-6.1 TerraOpenAI
IndexAll categories, out of 100.
73.8 ±1.9
77.1 ±3.8 best
GapIndex points below the top.
−3.3 · no clear gap
Top
CoverageIndex weight that has results.
100% best
90%
SpeedOutput tokens per second.
48/s best
46/s
EloLMArena rating and rank.
1502
—
ReleasedMonth of release.
2026-07
2026-10
Input / 1MUS dollars per 1M input tokens.
$5.00
$1.00 best
Output / 1MUS dollars per 1M output tokens.
$25.00
$5.00 best
Batch output / 1MBatch price per 1M output tokens.
$12.50
$2.50 best
1K chats2K tokens in, 500 out, each.
$22.50
$4.50 best
1K documents20K tokens in, 1K out, each.
$125.00
$25.00 best
1K agent tasks200K tokens in, 20K out, each.
$1,500.00
$300.00 best
ContextMaximum tokens in one request.
1M
1.05M best
AgenticMulti-step tasks with tools.
71.6
78.6 best
CodingCode writing and repair.
74.8 best
74.4
ReasoningLogic problems and puzzles.
75.4
81.3 best
MultimodalTasks with images and text.
72.5
73.2 best
KnowledgeFacts and expert knowledge.
73.1 best
70.5
MultilingualTasks in many languages.
63.6
—
InstructionTasks with strict prompt rules.
55.6
—
MathMath problems.
74.8
76.9 best

Benchmarks

33 shared
Only Claude Opus 5: 117Only GPT-6.1 Terra: 17
Claude Opus 5
GPT-6.1 Terra
Artificial Analysis Humanity's Last ExamKnowledge
54.9% best7 / 222
46.2%24 / 222
Artificial Analysis Long Context ReasoningReasoning
79.3%52 / 217
82.7% best23 / 217
GPQA diamond · Epoch AIKnowledge
93.9%14 / 217
94.3% best10 / 217
Critical Physics TasksReasoning
29.1% best13 / 214
28.0%16 / 214
OTIS Mock AIME 2024-2025Math
98.9%22 / 200
100.0% best1 / 200
Artificial Analysis Omniscience AccuracyKnowledge
60.9% best7 / 164
47.6%28 / 164
Vibe Code Bench v1.1Coding
88.4% best11 / 123
84.0%19 / 123
Artificial Analysis SciCodeCoding
56.4% best26 / 114
55.1%28 / 114
Artificial Analysis MMMU-ProMultimodal
84.7%6 / 113
84.7%6 / 113
SimpleQA VerifiedKnowledge
59.9% best19 / 91
57.3%21 / 91
FrontierMath-Tiers-1-3-v2-PrivateMath
85.6%15 / 90
90.9% best5 / 90
Legal Research BenchLegal
55.3% best2 / 90
26.0%62 / 90
Tax Agent BenchFinance
47.1% best5 / 82
17.1%58 / 82
LiveBench Data AnalysisReasoning
74.6%40 / 80
82.3% best4 / 80
LiveBench ReasoningReasoning
91.2% best8 / 80
88.7%20 / 80
Mystery Game PuzzlesReasoning
59.0%9 / 80
74.0% best4 / 80
FrontierMath-Tier-4-v2-PrivateMath
73.2%15 / 72
92.7% best6 / 72
Terminal-Bench 4.0Agentic
53.5% best10 / 61
49.5%11 / 61
Agent Arena steerabilityAgentic
4.417 / 54
16.6 best4 / 54
Agent Arena task outcomeAgentic
10.2 best10 / 54
9.711 / 54