Noometry

Model comparison

Claude Fable 5.1 vs DeepSeek-V3

Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 39.5 on the Noometry Index. DeepSeek-V3 costs 49× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.

Last verified . 25 shared benchmarks.

Claude Fable 5.1 Anthropic

69.0

Rank #2 Confirmed

DeepSeek-V3 DeepSeek

39.5

Rank #166 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Claude Fable 5.1 scores higher in 8 categories and DeepSeek-V3 in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Fable 5.1 leads 89.6 to 32.1.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 100% for Claude Fable 5.1 and 37.8% for DeepSeek-V3.
  • DeepSeek-V3 is cheaper at $0.24 / $0.90 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
  • Claude Fable 5.1 accepts more context: 1M tokens versus 164K.
  • DeepSeek-V3 has downloadable open weights; the other is API-only.

Side by side

Claude Fable 5.1DeepSeek-V3
ProviderAnthropicDeepSeek
Noometry Index69.039.5
Released2026-09-012024-12-26
WeightsProprietaryOpen
Context window1M164K
Max output128K164K
Input $ / M tokens$10$0.24
Output $ / M tokens$50$0.90
Results tracked5260

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Claude Fable 5.1 leads

Claude Fable 5.1: 74.7 (#1), DeepSeek-V3: 42.3 (#106)

BenchmarkClaude Fable 5.1DeepSeek-V3
SciCode63.1%35.8%
WeirdML92.9%36.1%
LMArena Coding15281368
FrontierCode50.9%—
Aider Polyglot—55.1%
CursorBench51.8%—
LMArena WebDev1744—
FrontierSWE56.3%—
GSO88.2%—
BigCodeBench Instruct—50%
LiveBench Coding—70.9%
MirrorCode73.3%—
BigCodeBench Complete—62.2%
ALE-Bench2,143—
HumanEval+—86.6%
MBPP+—73%

Agentic & Tool Use Not comparable

Claude Fable 5.1: 50.7 (#5), DeepSeek-V3: —

BenchmarkClaude Fable 5.1DeepSeek-V3
APEX-Agents68.6%—
Remote Labor Index17.9%—
GDP.pdf29.6%—
METR Time Horizons—49.6%
Vending-Bench 25,422—

Reasoning Claude Fable 5.1 leads

Claude Fable 5.1: 76.7 (#7), DeepSeek-V3: 20.5 (#236)

BenchmarkClaude Fable 5.1DeepSeek-V3
CritPt31.1%0%
LMArena Hard Prompts15261365
DTBench97.6%64.8%
LMCA65.5%15.5%
Epoch Capabilities Index164.7135.94
ARC-AGI-290%—
SimpleBench—27.2%
Kagi LLM Benchmark—52.3%
NYT Connections (extended)90%—
ARC-AGI-197.5%—
Chess Puzzles47%—
EBR-Bench57.1%—
LiveBench Reasoning—65.8%
Mystery Game Puzzles58%—
LiveBench Data Analysis—60.9%
BIG-Bench Hard—87.5%
ForecastBench—59.1
HellaSwag—88.9%
LiveBench—66.9%
PIQA—84.7%
WinoGrande—85.2%

Math Claude Fable 5.1 leads

Claude Fable 5.1: 89.6 (#4), DeepSeek-V3: 32.1 (#219)

BenchmarkClaude Fable 5.1DeepSeek-V3
OTIS Mock AIME 2024-2025100%37.8%
LMArena Math15251373
FrontierMath (Tiers 1-3)90.2%—
FrontierMath Tier 487.8%—
ProofBench100%—
Omni-MATH—40.3%
LiveBench Math—73.5%
MATH Level 5—75.5%
FrontierMath (Feb 2025 set)—1.7%
FrontierMath Erdős0%—

Knowledge Claude Fable 5.1 leads

Claude Fable 5.1: 69.6 (#6), DeepSeek-V3: 37.5 (#155)

BenchmarkClaude Fable 5.1DeepSeek-V3
LMArena Expert15351351
GPQA Diamond—67.6%
Humanity's Last Exam46.5%—
SimpleQA Verified70.8%—
MMLU-Pro—72.3%
Confabulations—26.1%
Vectara Hallucination Rate—6.1%
GPQA (HELM)—53.8%
ARC (AI2) Challenge—95.3%
MMLU—87.2%
TriviaQA—82.9%

Multimodal Not comparable

Claude Fable 5.1: 53.9 (#4), DeepSeek-V3: —

BenchmarkClaude Fable 5.1DeepSeek-V3
LMArena Vision1318—
Blueprint-Bench 241.9%—
Furniture Assembly70%—
LMArena Document1513—

Multilingual Claude Fable 5.1 leads

Claude Fable 5.1: 59.1 (#3), DeepSeek-V3: 48.5 (#143)

BenchmarkClaude Fable 5.1DeepSeek-V3
LMArena Non-English15071358
LMArena Chinese15861391
LMArena French15251385
LMArena German15001374
LMArena Japanese15431333
LMArena Korean15341319
LMArena Russian15211373
LMArena Spanish15161358

Instruction Following Claude Fable 5.1 leads

Claude Fable 5.1: 79.2 (#6), DeepSeek-V3: 72.8 (#130)

BenchmarkClaude Fable 5.1DeepSeek-V3
LMArena Instruction Following15171345
LiveBench Instruction Following—81.5%
IFEval—83.2%

Long Context Claude Fable 5.1 leads

Claude Fable 5.1: 46.7 (#20), DeepSeek-V3: 34.0 (#253)

BenchmarkClaude Fable 5.1DeepSeek-V3
LMArena Longer Query15221352
Fiction.LiveBench—50%

Writing & Preference Claude Fable 5.1 leads

Claude Fable 5.1: 79.2 (#2), DeepSeek-V3: 57.4 (#130)

BenchmarkClaude Fable 5.1DeepSeek-V3
LMArena Text15101375
LMArena Creative Writing15071364
EQ-Bench Creative Writing21621472
LMArena Multi-Turn14921389
Short-Story Creative Writing—77%
WildBench—83%
LiveBench Language—49.1%

Frequently asked questions

Is Claude Fable 5.1 better than DeepSeek-V3?

Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 39.5 on the Noometry Index. DeepSeek-V3 costs 49× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.

Which is cheaper, Claude Fable 5.1 or DeepSeek-V3?

DeepSeek-V3 is cheaper. It lists at $0.24 per million input tokens and $0.90 per million output tokens; Claude Fable 5.1 lists at $10 and $50.

Is Claude Fable 5.1 or DeepSeek-V3 better for coding?

Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 42.3 in the Noometry coding category.

Which has the bigger context window?

Claude Fable 5.1 does, with 1M tokens against 164K.

How many benchmarks do Claude Fable 5.1 and DeepSeek-V3 share?

25 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and DeepSeek-V3 has 60.

Related comparisons

Go deeper