Model comparison

DeepSeek-V3.1-Terminus vs Llama 3.1-8B

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 23.0 on the Noometry Index. Llama 3.1-8B costs 7.9× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.

Last verified October 12, 2026. 14 shared benchmarks.

DeepSeek-V3.1-Terminus

DeepSeek

43.1

Rank #97 Confirmed

Llama 3.1-8B

Summary

They share 14 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Llama 3.1-8B in 0 categories; 7 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.0 to 29.7.
The biggest single-benchmark swing is DTBench: 81.3% for DeepSeek-V3.1-Terminus and 50.9% for Llama 3.1-8B.
Llama 3.1-8B is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.27 / $1 for DeepSeek-V3.1-Terminus.
DeepSeek-V3.1-Terminus accepts more context: 164K tokens versus 128K.

Side by side

DeepSeek-V3.1-Terminus and Llama 3.1-8B specifications
	DeepSeek-V3.1-Terminus	Llama 3.1-8B
Provider	DeepSeek	Meta
Noometry Index	43.1	23.0
Released	2025-09-22	2024-07-23
Weights	Open	Open
Context window	164K	128K
Max output	147K	4K
Input $ / M tokens	$0.27	$0.05
Output $ / M tokens	$1	$0.08
Results tracked	16	43

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

Category by category

Coding DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 42.0 (#113), Llama 3.1-8B: 20.2 (#340)

Coding benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Llama 3.1-8B
SciCode	40.6%	13.2%
LMArena Coding	1426	1195
WeirdML	—	1.7%
BigCodeBench Instruct	—	32.8%
BigCodeBench Complete	—	40.5%
ALE-Bench	745.17	—
HumanEval+	—	62.8%
MBPP+	—	55.6%

Agentic & Tool Use Not comparable

DeepSeek-V3.1-Terminus: —, Llama 3.1-8B: 22.5 (#131)

Agentic & Tool Use benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Llama 3.1-8B
Berkeley Function Calling Leaderboard	—	25.8%
BALROG	—	15.1%

Reasoning DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 26.4 (#133), Llama 3.1-8B: 14.9 (#321)

Reasoning benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Llama 3.1-8B
CritPt	1.7%	0%
LMArena Hard Prompts	1426	1175
DTBench	81.3%	50.9%
LMCA	28.6%	5.4%
Kagi LLM Benchmark	57.4%	—
Chess Puzzles	—	0%
Epoch Capabilities Index	—	116.57
PIQA	—	81.2%

Math DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 38.5 (#137), Llama 3.1-8B: 10.2 (#317)

Math benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Llama 3.1-8B
LMArena Math	1402	1179
OTIS Mock AIME 2024-2025	—	1.7%
Omni-MATH	—	13.7%
MATH Level 5	—	22.9%
GSM8K	—	82.4%

Knowledge Not comparable

DeepSeek-V3.1-Terminus: —, Llama 3.1-8B: 8.0 (#307)

Knowledge benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Llama 3.1-8B
GPQA Diamond	—	27%
MMLU-Pro	—	40.6%
GPQA (HELM)	—	24.7%
LMArena Expert	—	1144
BoolQ	—	82.8%
MMLU	—	56.1%

Multilingual DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 52.1 (#92), Llama 3.1-8B: 34.0 (#249)

Multilingual benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Llama 3.1-8B
LMArena Non-English	1407	1148
LMArena Russian	1436	1158
LMArena Chinese	—	1151
LMArena French	—	1177
LMArena German	—	1144
LMArena Japanese	—	1061
LMArena Korean	—	1053
LMArena Spanish	—	1169

Instruction Following DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 74.0 (#106), Llama 3.1-8B: 58.9 (#258)

Instruction Following benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Llama 3.1-8B
LMArena Instruction Following	1404	1159
IFEval	—	74.3%

Long Context DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 43.4 (#97), Llama 3.1-8B: 35.8 (#238)

Long Context benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Llama 3.1-8B
LMArena Longer Query	1421	1182

Writing & Preference DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 61.0 (#92), Llama 3.1-8B: 29.7 (#290)

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Llama 3.1-8B
LMArena Text	1419	1187
LMArena Creative Writing	1403	1154
LMArena Multi-Turn	1411	1172
EQ-Bench Creative Writing	—	713
WildBench	—	68.7%

Frequently asked questions

Is DeepSeek-V3.1-Terminus better than Llama 3.1-8B?

Which is cheaper, DeepSeek-V3.1-Terminus or Llama 3.1-8B?

Llama 3.1-8B is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; DeepSeek-V3.1-Terminus lists at $0.27 and $1.

Is DeepSeek-V3.1-Terminus or Llama 3.1-8B better for coding?

DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 20.2 in the Noometry coding category.

Which has the bigger context window?

DeepSeek-V3.1-Terminus does, with 164K tokens against 128K.

How many benchmarks do DeepSeek-V3.1-Terminus and Llama 3.1-8B share?

14 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Llama 3.1-8B has 43.