Model comparison

C4ai Aya Expanse 8b vs DeepSeek-V3

DeepSeek-V3 is the stronger model overall, scoring 39.5 to 34.9 on the Noometry Index.

Last verified October 10, 2026. 15 shared benchmarks.

C4ai Aya Expanse 8b

Cohere

34.9

Rank #229 Confirmed

DeepSeek-V3

DeepSeek

39.5

Rank #166 Confirmed

Summary

They share 15 benchmarks with published results for both. C4ai Aya Expanse 8b scores higher in 3 categories and DeepSeek-V3 in 5 categories; 8 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where DeepSeek-V3 leads 57.4 to 39.0.

Side by side

C4ai Aya Expanse 8b and DeepSeek-V3 specifications
	C4ai Aya Expanse 8b	DeepSeek-V3
Provider	Cohere	DeepSeek
Noometry Index	34.9	39.5
Released	—	2024-12-26
Weights	Open	Open
Context window	—	164K
Max output	—	164K
Input $ / M tokens	—	$0.24
Output $ / M tokens	—	$0.90
Results tracked	15	60

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

Category by category

Coding DeepSeek-V3 leads

C4ai Aya Expanse 8b: 33.8 (#252), DeepSeek-V3: 42.3 (#106)

Coding benchmarks
Benchmark	C4ai Aya Expanse 8b	DeepSeek-V3
LMArena Coding	1160	1368
Aider Polyglot	—	55.1%
SciCode	—	35.8%
WeirdML	—	36.1%
BigCodeBench Instruct	—	50%
LiveBench Coding	—	70.9%
BigCodeBench Complete	—	62.2%
HumanEval+	—	86.6%
MBPP+	—	73%

Agentic & Tool Use Not comparable

C4ai Aya Expanse 8b: —, DeepSeek-V3: —

Agentic & Tool Use benchmarks
Benchmark	C4ai Aya Expanse 8b	DeepSeek-V3
METR Time Horizons	—	49.6%

Reasoning C4ai Aya Expanse 8b leads

C4ai Aya Expanse 8b: 22.4 (#197), DeepSeek-V3: 20.5 (#236)

Reasoning benchmarks
Benchmark	C4ai Aya Expanse 8b	DeepSeek-V3
LMArena Hard Prompts	1156	1365
SimpleBench	—	27.2%
Kagi LLM Benchmark	—	52.3%
CritPt	—	0%
LiveBench Reasoning	—	65.8%
DTBench	—	64.8%
LiveBench Data Analysis	—	60.9%
LMCA	—	15.5%
BIG-Bench Hard	—	87.5%
Epoch Capabilities Index	—	135.94
ForecastBench	—	59.1
HellaSwag	—	88.9%
LiveBench	—	66.9%
PIQA	—	84.7%
WinoGrande	—	85.2%

Math C4ai Aya Expanse 8b leads

C4ai Aya Expanse 8b: 33.3 (#203), DeepSeek-V3: 32.1 (#219)

Math benchmarks
Benchmark	C4ai Aya Expanse 8b	DeepSeek-V3
LMArena Math	1168	1373
OTIS Mock AIME 2024-2025	—	37.8%
Omni-MATH	—	40.3%
LiveBench Math	—	73.5%
MATH Level 5	—	75.5%
FrontierMath (Feb 2025 set)	—	1.7%

Knowledge DeepSeek-V3 leads

C4ai Aya Expanse 8b: 33.6 (#201), DeepSeek-V3: 37.5 (#155)

Knowledge benchmarks
Benchmark	C4ai Aya Expanse 8b	DeepSeek-V3
Vectara Hallucination Rate	9.5%	6.1%
LMArena Expert	1153	1351
GPQA Diamond	—	67.6%
MMLU-Pro	—	72.3%
Confabulations	—	26.1%
GPQA (HELM)	—	53.8%
ARC (AI2) Challenge	—	95.3%
MMLU	—	87.2%
TriviaQA	—	82.9%

Multilingual DeepSeek-V3 leads

C4ai Aya Expanse 8b: 36.1 (#242), DeepSeek-V3: 48.5 (#143)

Multilingual benchmarks
Benchmark	C4ai Aya Expanse 8b	DeepSeek-V3
LMArena Non-English	1180	1358
LMArena Chinese	1181	1391
LMArena German	1188	1374
LMArena Japanese	1120	1333
LMArena Russian	1197	1373
LMArena French	—	1385
LMArena Korean	—	1319
LMArena Spanish	—	1358

Instruction Following DeepSeek-V3 leads

C4ai Aya Expanse 8b: 60.1 (#253), DeepSeek-V3: 72.8 (#130)

Instruction Following benchmarks
Benchmark	C4ai Aya Expanse 8b	DeepSeek-V3
LMArena Instruction Following	1155	1345
LiveBench Instruction Following	—	81.5%
IFEval	—	83.2%

Long Context C4ai Aya Expanse 8b leads

C4ai Aya Expanse 8b: 36.1 (#236), DeepSeek-V3: 34.0 (#253)

Long Context benchmarks
Benchmark	C4ai Aya Expanse 8b	DeepSeek-V3
LMArena Longer Query	1191	1352
Fiction.LiveBench	—	50%

Writing & Preference DeepSeek-V3 leads

C4ai Aya Expanse 8b: 39.0 (#250), DeepSeek-V3: 57.4 (#130)

Writing & Preference benchmarks
Benchmark	C4ai Aya Expanse 8b	DeepSeek-V3
LMArena Text	1185	1375
LMArena Creative Writing	1168	1364
LMArena Multi-Turn	1160	1389
Short-Story Creative Writing	—	77%
EQ-Bench Creative Writing	—	1472
WildBench	—	83%
LiveBench Language	—	49.1%

Frequently asked questions

Is C4ai Aya Expanse 8b better than DeepSeek-V3?