Noometry

Model comparison

GPT-4.1 mini vs Llama 3.1-70B

GPT-4.1 mini is the stronger model overall, scoring 33.6 to 29.6 on the Noometry Index. Llama 3.1-70B costs 1.8× less per token, which makes it the better buy when GPT-4.1 mini's lead doesn't matter for your workload.

Last verified . 31 shared benchmarks.

GPT-4.1 mini OpenAI

33.6

Rank #240 Confirmed

Llama 3.1-70B Meta

29.6

Rank #308 Confirmed

Summary

  • They share 31 benchmarks with published results for both. GPT-4.1 mini scores higher in 7 categories and Llama 3.1-70B in 2 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GPT-4.1 mini leads 48.6 to 35.4.
  • The biggest single-benchmark swing is MATH Level 5: 87.3% for GPT-4.1 mini and 36.7% for Llama 3.1-70B.
  • Llama 3.1-70B is cheaper at $0.40 / $0.40 per million input/output tokens, against $0.40 / $1.60 for GPT-4.1 mini.
  • GPT-4.1 mini accepts more context: 1.05M tokens versus 128K.
  • Llama 3.1-70B has downloadable open weights; the other is API-only.

Side by side

GPT-4.1 miniLlama 3.1-70B
ProviderOpenAIMeta
Noometry Index33.629.6
Released2025-04-142024-07-23
WeightsProprietaryOpen
Context window1.05M128K
Max output33K4K
Input $ / M tokens$0.40$0.40
Output $ / M tokens$1.60$0.40
Results tracked4735

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

Category by category

Coding Too close to call

GPT-4.1 mini: 30.6 (#293), Llama 3.1-70B: 30.3 (#296)

BenchmarkGPT-4.1 miniLlama 3.1-70B
WeirdML37.6%9%
BigCodeBench Instruct48.9%46.1%
LMArena Coding13671260
SWE-bench Verified (bash only)23.9%—
Aider Polyglot32.4%—
SciCode40.4%—
BigCodeBench Complete—54.8%
CadEval16%—

Agentic & Tool Use GPT-4.1 mini leads

GPT-4.1 mini: 33.3 (#55), Llama 3.1-70B: 25.1 (#112)

BenchmarkGPT-4.1 miniLlama 3.1-70B
Berkeley Function Calling Leaderboard50.5%—
TheAgentCompany—6.9%
BALROG—27.9%

Reasoning Llama 3.1-70B leads

GPT-4.1 mini: 10.8 (#340), Llama 3.1-70B: 21.6 (#220)

BenchmarkGPT-4.1 miniLlama 3.1-70B
LMArena Hard Prompts13491241
DTBench68.8%60%
LMCA21.1%14.8%
Epoch Capabilities Index135.01125.92
ARC-AGI-20%—
Kagi LLM Benchmark48.6%—
ARC-AGI-13.5%—
CritPt0%—
Chess Puzzles7%—
Mystery Game Puzzles7%—

Math GPT-4.1 mini leads

GPT-4.1 mini: 24.1 (#270), Llama 3.1-70B: 13.5 (#304)

BenchmarkGPT-4.1 miniLlama 3.1-70B
OTIS Mock AIME 2024-202544.7%3.6%
Omni-MATH49.1%21%
LMArena Math13431252
MATH Level 587.3%36.7%
FrontierMath (Tiers 1-3)6.7%—
FrontierMath (Feb 2025 set)4.5%—

Knowledge GPT-4.1 mini leads

GPT-4.1 mini: 34.7 (#194), Llama 3.1-70B: 24.2 (#269)

BenchmarkGPT-4.1 miniLlama 3.1-70B
GPQA Diamond65.8%44.2%
MMLU-Pro78.3%65.3%
GPQA (HELM)61.4%42.6%
LMArena Expert13381209
SimpleQA Verified12.7%—
MMLU—80.1%

Multimodal Not comparable

GPT-4.1 mini: 35.8 (#82), Llama 3.1-70B: —

BenchmarkGPT-4.1 miniLlama 3.1-70B
LMArena Vision1181—

Multilingual GPT-4.1 mini leads

GPT-4.1 mini: 45.7 (#166), Llama 3.1-70B: 38.8 (#225)

BenchmarkGPT-4.1 miniLlama 3.1-70B
LMArena Non-English13181219
LMArena Chinese13291215
LMArena French13581261
LMArena German13511222
LMArena Japanese12901132
LMArena Korean12981140
LMArena Russian13241234
LMArena Spanish13191253

Instruction Following GPT-4.1 mini leads

GPT-4.1 mini: 73.7 (#118), Llama 3.1-70B: 65.3 (#223)

BenchmarkGPT-4.1 miniLlama 3.1-70B
IFEval90.4%82.1%
LMArena Instruction Following13331231

Long Context Llama 3.1-70B leads

GPT-4.1 mini: 31.8 (#275), Llama 3.1-70B: 37.6 (#214)

BenchmarkGPT-4.1 miniLlama 3.1-70B
LMArena Longer Query13441241
Fiction.LiveBench44.4%—

Writing & Preference GPT-4.1 mini leads

GPT-4.1 mini: 48.6 (#199), Llama 3.1-70B: 35.4 (#267)

BenchmarkGPT-4.1 miniLlama 3.1-70B
LMArena Text13401261
LMArena Creative Writing13001232
EQ-Bench Creative Writing1147784
WildBench83.8%75.8%
LMArena Multi-Turn13541256

Frequently asked questions

Is GPT-4.1 mini better than Llama 3.1-70B?

GPT-4.1 mini is the stronger model overall, scoring 33.6 to 29.6 on the Noometry Index. Llama 3.1-70B costs 1.8× less per token, which makes it the better buy when GPT-4.1 mini's lead doesn't matter for your workload.

Which is cheaper, GPT-4.1 mini or Llama 3.1-70B?

Llama 3.1-70B is cheaper. It lists at $0.40 per million input tokens and $0.40 per million output tokens; GPT-4.1 mini lists at $0.40 and $1.60.

Is GPT-4.1 mini or Llama 3.1-70B better for coding?

They score almost the same on coding (30.6 vs 30.3); test both on your own repository before choosing.

Which has the bigger context window?

GPT-4.1 mini does, with 1.05M tokens against 128K.

How many benchmarks do GPT-4.1 mini and Llama 3.1-70B share?

31 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Llama 3.1-70B has 35.

Related comparisons

Go deeper