Noometry

Model comparison

GPT-5.1 vs Grok 4.20 (Non-Reasoning)

GPT-5.1 and Grok 4.20 (Non-Reasoning) score almost the same on the Noometry Index (49.0 vs 48.6), so choose on price, context window or the category you care about most.

Last verified . 37 shared benchmarks.

GPT-5.1 OpenAI

49.0

Rank #53 Confirmed

Grok 4.20 (Non-Reasoning) xAI

48.6

Rank #54 Confirmed

Summary

  • They share 37 benchmarks with published results for both. GPT-5.1 scores higher in 5 categories and Grok 4.20 (Non-Reasoning) in 5 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 39.8.
  • The biggest single-benchmark swing is ARC-AGI-2: 17.6% for GPT-5.1 and 65.1% for Grok 4.20 (Non-Reasoning).
  • Grok 4.20 (Non-Reasoning) is cheaper at $1.25 / $2.50 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
  • Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 400K.

Side by side

GPT-5.1Grok 4.20 (Non-Reasoning)
ProviderOpenAIxAI
Noometry Index49.048.6
Released2025-11-132026-02-17
WeightsProprietaryProprietary
Context window400K1M
Max output128K30K
Input $ / M tokens$1.25$1.25
Output $ / M tokens$10$2.50
Results tracked6346

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

Category by category

Coding GPT-5.1 leads

GPT-5.1: 46.4 (#66), Grok 4.20 (Non-Reasoning): 42.1 (#112)

BenchmarkGPT-5.1Grok 4.20 (Non-Reasoning)
LMArena WebDev13951375
WeirdML60.8%52.3%
LMArena Coding14541459
ALE-Bench1,1921,150
SWE-bench Verified68%—
SWE-bench Verified (bash only)66%—
SciCode43.3%—
GSO13.7%—
LiveBench Coding72.5%—

Agentic & Tool Use Grok 4.20 (Non-Reasoning) leads

GPT-5.1: 32.7 (#60), Grok 4.20 (Non-Reasoning): 34.4 (#46)

BenchmarkGPT-5.1Grok 4.20 (Non-Reasoning)
Terminal-Bench47.6%57.3%
LMArena Search11991189
Vending-Bench 21,4734,663
τ²-bench Banking—18%
DeepResearch Bench42.8%—

Reasoning Grok 4.20 (Non-Reasoning) leads

GPT-5.1: 39.8 (#58), Grok 4.20 (Non-Reasoning): 52.3 (#32)

BenchmarkGPT-5.1Grok 4.20 (Non-Reasoning)
ARC-AGI-217.6%65.1%
ARC-AGI-172.8%89.5%
Chess Puzzles32%24%
LMArena Hard Prompts14571451
DTBench90.1%90.1%
LMCA43.9%38.7%
Epoch Capabilities Index149.64151.98
ForecastBench58.161.4
SimpleBench53.2%—
Kagi LLM Benchmark—75%
NYT Connections (extended)—85.4%
CritPt4.9%—
EnigmaEval11.2%—
Thematic Generalization—63.8%
LiveBench Reasoning95.8%—
Mystery Game Puzzles19%—
LiveBench Data Analysis72.1%—
LiveBench78.8%—

Math GPT-5.1 leads

GPT-5.1: 52.2 (#51), Grok 4.20 (Non-Reasoning): 48.2 (#65)

BenchmarkGPT-5.1Grok 4.20 (Non-Reasoning)
OTIS Mock AIME 2024-202588.6%92.2%
LMArena Math14471455
FrontierMath (Tiers 1-3)—44.9%
FrontierMath Tier 4—17.1%
ProofBench—14%
Omni-MATH46.4%—
LiveBench Math94.5%—
FrontierMath (Feb 2025 set)31%—
FrontierMath Tier 4 (v1)12.5%—

Knowledge Grok 4.20 (Non-Reasoning) leads

GPT-5.1: 50.6 (#71), Grok 4.20 (Non-Reasoning): 52.8 (#60)

BenchmarkGPT-5.1Grok 4.20 (Non-Reasoning)
GPQA Diamond87.6%89.3%
SimpleQA Verified48%30.2%
LMArena Expert14701439
Humanity's Last Exam23.7%—
MMLU-Pro57.9%—
Vectara Hallucination Rate10.9%—
GPQA (HELM)44.2%—

Multimodal GPT-5.1 leads

GPT-5.1: 44.8 (#19), Grok 4.20 (Non-Reasoning): 33.3 (#98)

BenchmarkGPT-5.1Grok 4.20 (Non-Reasoning)
LMArena Vision12501263
LMArena Document14031416
VPCT58.7%—
Blueprint-Bench 2—0%

Multilingual Too close to call

GPT-5.1: 53.8 (#56), Grok 4.20 (Non-Reasoning): 54.5 (#40)

BenchmarkGPT-5.1Grok 4.20 (Non-Reasoning)
LMArena Non-English14311441
LMArena Chinese14951481
LMArena French14501476
LMArena German14381465
LMArena Japanese14531449
LMArena Korean14011417
LMArena Russian14351458
LMArena Spanish14331443

Instruction Following GPT-5.1 leads

GPT-5.1: 83.9 (#1), Grok 4.20 (Non-Reasoning): 74.8 (#83)

BenchmarkGPT-5.1Grok 4.20 (Non-Reasoning)
LMArena Instruction Following14431420
LiveBench Instruction Following93.3%—
IFEval93.5%—

Long Context GPT-5.1 leads

GPT-5.1: 47.6 (#14), Grok 4.20 (Non-Reasoning): 45.5 (#34)

BenchmarkGPT-5.1Grok 4.20 (Non-Reasoning)
CL-bench23.7%22.2%
CL-bench Life17.3%11.9%
LMArena Longer Query14471437

Writing & Preference Grok 4.20 (Non-Reasoning) leads

GPT-5.1: 64.5 (#55), Grok 4.20 (Non-Reasoning): 65.7 (#44)

BenchmarkGPT-5.1Grok 4.20 (Non-Reasoning)
LMArena Text14431451
LMArena Creative Writing14271438
LMArena Multi-Turn14501456
EQ-Bench Creative Writing—1574
WildBench86.3%—
LiveBench Language80.2%—

Frequently asked questions

Is GPT-5.1 better than Grok 4.20 (Non-Reasoning)?

GPT-5.1 and Grok 4.20 (Non-Reasoning) score almost the same on the Noometry Index (49.0 vs 48.6), so choose on price, context window or the category you care about most.

Which is cheaper, GPT-5.1 or Grok 4.20 (Non-Reasoning)?

Grok 4.20 (Non-Reasoning) is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; GPT-5.1 lists at $1.25 and $10.

Is GPT-5.1 or Grok 4.20 (Non-Reasoning) better for coding?

GPT-5.1 scores higher on coding benchmarks: 46.4 versus 42.1 in the Noometry coding category.

Which has the bigger context window?

Grok 4.20 (Non-Reasoning) does, with 1M tokens against 400K.

How many benchmarks do GPT-5.1 and Grok 4.20 (Non-Reasoning) share?

37 benchmarks have published results for both models. GPT-5.1 has 63 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.

Related comparisons

Go deeper