Noometry

Model comparison

GPT-3.5-turbo vs Grok 4.20 (Non-Reasoning)

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 23.2 on the Noometry Index. GPT-3.5-turbo costs 2.1× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.

Last verified . 27 shared benchmarks.

GPT-3.5-turbo OpenAI

23.2

Rank #350 Confirmed

Grok 4.20 (Non-Reasoning) xAI

48.6

Rank #54 Confirmed

Summary

  • They share 27 benchmarks with published results for both. GPT-3.5-turbo scores higher in 0 categories and Grok 4.20 (Non-Reasoning) in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok 4.20 (Non-Reasoning) leads 52.8 to 10.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.2% for GPT-3.5-turbo and 92.2% for Grok 4.20 (Non-Reasoning).
  • GPT-3.5-turbo is cheaper at $0.50 / $1.50 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
  • Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 16K.

Side by side

GPT-3.5-turboGrok 4.20 (Non-Reasoning)
ProviderOpenAIxAI
Noometry Index23.248.6
Released2023-03-012026-02-17
WeightsProprietaryProprietary
Context window16K1M
Max output4K30K
Input $ / M tokens$0.50$1.25
Output $ / M tokens$1.50$2.50
Results tracked4446

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

Category by category

Coding Grok 4.20 (Non-Reasoning) leads

GPT-3.5-turbo: 23.9 (#331), Grok 4.20 (Non-Reasoning): 42.1 (#112)

BenchmarkGPT-3.5-turboGrok 4.20 (Non-Reasoning)
WeirdML3.5%52.3%
LMArena Coding11361459
LMArena WebDev—1375
BigCodeBench Instruct39.1%—
BigCodeBench Complete50.6%—
ALE-Bench—1,150
HumanEval+70.7%—
MBPP+69.7%—

Agentic & Tool Use Not comparable

GPT-3.5-turbo: —, Grok 4.20 (Non-Reasoning): 34.4 (#46)

BenchmarkGPT-3.5-turboGrok 4.20 (Non-Reasoning)
Terminal-Bench—57.3%
τ²-bench Banking—18%
LMArena Search—1189
METR Time Horizons21.5%—
Vending-Bench 2—4,663

Reasoning Grok 4.20 (Non-Reasoning) leads

GPT-3.5-turbo: 13.8 (#332), Grok 4.20 (Non-Reasoning): 52.3 (#32)

BenchmarkGPT-3.5-turboGrok 4.20 (Non-Reasoning)
Chess Puzzles0%24%
LMArena Hard Prompts11081451
DTBench48.5%90.1%
LMCA9.7%38.7%
Epoch Capabilities Index118.55151.98
ForecastBench50.461.4
ARC-AGI-2—65.1%
Kagi LLM Benchmark—75%
NYT Connections (extended)—85.4%
ARC-AGI-1—89.5%
Thematic Generalization—63.8%
Mystery Game Puzzles3%—
Adversarial NLI58.1%—
BIG-Bench Hard61.6%—
CommonsenseQA 2.057%—
WinoGrande81.6%—

Math Grok 4.20 (Non-Reasoning) leads

GPT-3.5-turbo: 6.3 (#327), Grok 4.20 (Non-Reasoning): 48.2 (#65)

BenchmarkGPT-3.5-turboGrok 4.20 (Non-Reasoning)
FrontierMath (Tiers 1-3)0%44.9%
OTIS Mock AIME 2024-20252.2%92.2%
LMArena Math11421455
FrontierMath Tier 4—17.1%
ProofBench—14%
MATH Level 515.9%—
GSM8K57.8%—

Knowledge Grok 4.20 (Non-Reasoning) leads

GPT-3.5-turbo: 10.0 (#303), Grok 4.20 (Non-Reasoning): 52.8 (#60)

BenchmarkGPT-3.5-turboGrok 4.20 (Non-Reasoning)
GPQA Diamond28%89.3%
LMArena Expert10701439
SimpleQA Verified—30.2%
ARC (AI2) Challenge87.4%—
BoolQ87%—
MMLU71.4%—
OpenBookQA86%—
TriviaQA85.8%—

Multimodal Not comparable

GPT-3.5-turbo: —, Grok 4.20 (Non-Reasoning): 33.3 (#98)

BenchmarkGPT-3.5-turboGrok 4.20 (Non-Reasoning)
LMArena Vision—1263
Blueprint-Bench 2—0%
LMArena Document—1416

Multilingual Grok 4.20 (Non-Reasoning) leads

GPT-3.5-turbo: 31.5 (#258), Grok 4.20 (Non-Reasoning): 54.5 (#40)

BenchmarkGPT-3.5-turboGrok 4.20 (Non-Reasoning)
LMArena Non-English11081441
LMArena Chinese10751481
LMArena French11181476
LMArena German10901465
LMArena Japanese10431449
LMArena Korean10191417
LMArena Russian11231458
LMArena Spanish11211443

Instruction Following Grok 4.20 (Non-Reasoning) leads

GPT-3.5-turbo: 57.9 (#262), Grok 4.20 (Non-Reasoning): 74.8 (#83)

BenchmarkGPT-3.5-turboGrok 4.20 (Non-Reasoning)
LMArena Instruction Following11191420

Long Context Grok 4.20 (Non-Reasoning) leads

GPT-3.5-turbo: 34.0 (#254), Grok 4.20 (Non-Reasoning): 45.5 (#34)

BenchmarkGPT-3.5-turboGrok 4.20 (Non-Reasoning)
LMArena Longer Query11211437
CL-bench—22.2%
CL-bench Life—11.9%

Writing & Preference Grok 4.20 (Non-Reasoning) leads

GPT-3.5-turbo: 25.3 (#305), Grok 4.20 (Non-Reasoning): 65.7 (#44)

BenchmarkGPT-3.5-turboGrok 4.20 (Non-Reasoning)
LMArena Text11251451
LMArena Creative Writing10921438
EQ-Bench Creative Writing4511574
LMArena Multi-Turn11171456

Frequently asked questions

Is GPT-3.5-turbo better than Grok 4.20 (Non-Reasoning)?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 23.2 on the Noometry Index. GPT-3.5-turbo costs 2.1× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.

Which is cheaper, GPT-3.5-turbo or Grok 4.20 (Non-Reasoning)?

GPT-3.5-turbo is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.

Is GPT-3.5-turbo or Grok 4.20 (Non-Reasoning) better for coding?

Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 23.9 in the Noometry coding category.

Which has the bigger context window?

Grok 4.20 (Non-Reasoning) does, with 1M tokens against 16K.

How many benchmarks do GPT-3.5-turbo and Grok 4.20 (Non-Reasoning) share?

27 benchmarks have published results for both models. GPT-3.5-turbo has 44 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.

Related comparisons

Go deeper