Noometry

Model comparison

GPT-4 Turbo vs Llama2 70b Steerlm Chat

Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 30.5 on the Noometry Index.

Last verified . 9 shared benchmarks.

GPT-4 Turbo OpenAI

30.5

Rank #292 Confirmed

Llama2 70b Steerlm Chat NVIDIA

31.8

Rank #268 Confirmed

Summary

  • They share 9 benchmarks with published results for both. GPT-4 Turbo scores higher in 5 categories and Llama2 70b Steerlm Chat in 2 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Llama2 70b Steerlm Chat leads 31.3 to 9.0.
  • Llama2 70b Steerlm Chat has downloadable open weights; the other is API-only.

Side by side

GPT-4 TurboLlama2 70b Steerlm Chat
ProviderOpenAINVIDIA
Noometry Index30.531.8
Released2023-11-06—
WeightsProprietaryOpen
Context window128K—
Max output4K—
Input $ / M tokens$10—
Output $ / M tokens$30—
Results tracked369

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

Category by category

Coding GPT-4 Turbo leads

GPT-4 Turbo: 33.8 (#249), Llama2 70b Steerlm Chat: 29.9 (#300)

BenchmarkGPT-4 TurboLlama2 70b Steerlm Chat
LMArena Coding12681025
WeirdML18%—
BigCodeBench Instruct48.2%—
BigCodeBench Complete58.2%—
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, Llama2 70b Steerlm Chat: —

BenchmarkGPT-4 TurboLlama2 70b Steerlm Chat
METR Time Horizons36.7%—

Reasoning Llama2 70b Steerlm Chat leads

GPT-4 Turbo: 15.3 (#317), Llama2 70b Steerlm Chat: 20.0 (#246)

BenchmarkGPT-4 TurboLlama2 70b Steerlm Chat
LMArena Hard Prompts12511047
SimpleBench25.1%—
Chess Puzzles6%—
DTBench61.6%—
LMCA9.8%—
Epoch Capabilities Index127.25—
ForecastBench59.4—

Math Llama2 70b Steerlm Chat leads

GPT-4 Turbo: 9.0 (#322), Llama2 70b Steerlm Chat: 31.3 (#226)

BenchmarkGPT-4 TurboLlama2 70b Steerlm Chat
LMArena Math12721072
FrontierMath (Tiers 1-3)0.7%—
OTIS Mock AIME 2024-20256.7%—
MATH Level 546.7%—

Knowledge Not comparable

GPT-4 Turbo: 24.3 (#268), Llama2 70b Steerlm Chat: —

BenchmarkGPT-4 TurboLlama2 70b Steerlm Chat
GPQA Diamond46.6%—
Confabulations28.4%—
LMArena Expert1223—
MMLU81.3%—

Multimodal Not comparable

GPT-4 Turbo: 30.6 (#110), Llama2 70b Steerlm Chat: —

BenchmarkGPT-4 TurboLlama2 70b Steerlm Chat
LMArena Vision1090—

Multilingual GPT-4 Turbo leads

GPT-4 Turbo: 40.5 (#216), Llama2 70b Steerlm Chat: 28.8 (#270)

BenchmarkGPT-4 TurboLlama2 70b Steerlm Chat
LMArena Non-English12451063
LMArena Chinese1242—
LMArena French1276—
LMArena German1259—
LMArena Japanese1194—
LMArena Korean1187—
LMArena Russian1259—
LMArena Spanish1260—

Instruction Following GPT-4 Turbo leads

GPT-4 Turbo: 65.8 (#216), Llama2 70b Steerlm Chat: 54.2 (#279)

BenchmarkGPT-4 TurboLlama2 70b Steerlm Chat
LMArena Instruction Following12491060

Long Context GPT-4 Turbo leads

GPT-4 Turbo: 38.0 (#206), Llama2 70b Steerlm Chat: 30.4 (#288)

BenchmarkGPT-4 TurboLlama2 70b Steerlm Chat
LMArena Longer Query1254998

Writing & Preference GPT-4 Turbo leads

GPT-4 Turbo: 47.7 (#206), Llama2 70b Steerlm Chat: 31.6 (#283)

BenchmarkGPT-4 TurboLlama2 70b Steerlm Chat
LMArena Text12721098
LMArena Creative Writing12691091
LMArena Multi-Turn12671058

Frequently asked questions

Is GPT-4 Turbo better than Llama2 70b Steerlm Chat?

Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 30.5 on the Noometry Index.

Is GPT-4 Turbo or Llama2 70b Steerlm Chat better for coding?

GPT-4 Turbo scores higher on coding benchmarks: 33.8 versus 29.9 in the Noometry coding category.

How many benchmarks do GPT-4 Turbo and Llama2 70b Steerlm Chat share?

9 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Llama2 70b Steerlm Chat has 9.

Related comparisons

Go deeper