Inference
EN

Claude Fable 5 vs GPT-6.1 Terra

Change models
Claude Fable 5Anthropic
GPT-6.1 TerraOpenAI
IndexAll categories, out of 100.
74.0 ±2.7
77.1 ±3.8 best
GapIndex points below the top.
−3.1 · no clear gap
Top
CoverageIndex weight that has results.
95% best
90%
SpeedOutput tokens per second.
56/s best
46/s
EloLMArena rating and rank.
1492
—
ReleasedMonth of release.
2026-06
2026-10
Input / 1MUS dollars per 1M input tokens.
$10.00
$1.00 best
Output / 1MUS dollars per 1M output tokens.
$50.00
$5.00 best
Batch output / 1MBatch price per 1M output tokens.
$25.00
$2.50 best
1K chats2K tokens in, 500 out, each.
$45.00
$4.50 best
1K documents20K tokens in, 1K out, each.
$250.00
$25.00 best
1K agent tasks200K tokens in, 20K out, each.
$3,000.00
$300.00 best
ContextMaximum tokens in one request.
1M
1.05M best
AgenticMulti-step tasks with tools.
71.4
78.6 best
CodingCode writing and repair.
74.7 best
74.4
ReasoningLogic problems and puzzles.
73.6
81.3 best
MultimodalTasks with images and text.
70.1
73.2 best
KnowledgeFacts and expert knowledge.
75.8 best
70.5
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
64.1
—
MathMath problems.
76.2
76.9 best

Benchmarks

29 shared
Only Claude Fable 5: 63Only GPT-6.1 Terra: 21
Claude Fable 5
GPT-6.1 Terra
Artificial Analysis Humanity's Last ExamKnowledge
55.5% best5 / 222
46.2%24 / 222
Artificial Analysis Long Context ReasoningReasoning
82.3%27 / 217
82.7% best23 / 217
GPQA diamond · Epoch AIKnowledge
85.9%69 / 217
94.3% best10 / 217
Critical Physics TasksReasoning
28.6% best14 / 214
28.0%16 / 214
OTIS Mock AIME 2024-2025Math
99.7%14 / 200
100.0% best1 / 200
Artificial Analysis Omniscience AccuracyKnowledge
65.4% best4 / 164
47.6%28 / 164
Vibe Code Bench v1.1Coding
90.4% best4 / 123
84.0%19 / 123
Artificial Analysis SciCodeCoding
61.0% best6 / 114
55.1%28 / 114
SimpleQA VerifiedKnowledge
70.7% best9 / 91
57.3%21 / 91
FrontierMath-Tiers-1-3-v2-PrivateMath
87.0%12 / 90
90.9% best5 / 90
Legal Research BenchLegal
49.5% best9 / 90
26.0%62 / 90
Tax Agent BenchFinance
38.3% best12 / 82
17.1%58 / 82
LiveBench Data AnalysisReasoning
80.5%8 / 80
82.3% best4 / 80
LiveBench ReasoningReasoning
89.7% best15 / 80
88.7%20 / 80
Mystery Game PuzzlesReasoning
52.0%14 / 80
74.0% best4 / 80
FrontierMath-Tier-4-v2-PrivateMath
90.2%7 / 72
92.7% best6 / 72
Terminal-Bench 4.0Agentic
41.4%14 / 61
49.5% best11 / 61
Agent Arena steerabilityAgentic
7.915 / 54
16.6 best4 / 54
Agent Arena task outcomeAgentic
5.114 / 54
9.7 best11 / 54
LiveBench Coding 2.0Coding
98.3% best1 / 52
90.8%11 / 52