Noometry

Model comparison

Gemini 2.5 Flash vs Grok 4.20 (Non-Reasoning)

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 1.8× 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 . 31 shared benchmarks.

Gemini 2.5 Flash Google

39.3

Rank #170 Confirmed

Grok 4.20 (Non-Reasoning) xAI

48.6

Rank #54 Confirmed

Summary

  • They share 31 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 3 categories and Grok 4.20 (Non-Reasoning) in 7 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 18.1.
  • The biggest single-benchmark swing is ARC-AGI-2: 2.5% for Gemini 2.5 Flash and 65.1% for Grok 4.20 (Non-Reasoning).
  • Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
  • Gemini 2.5 Flash accepts more context: 1.05M tokens versus 1M.

Side by side

Gemini 2.5 FlashGrok 4.20 (Non-Reasoning)
ProviderGooglexAI
Noometry Index39.348.6
Released2025-04-172026-02-17
WeightsProprietaryProprietary
Context window1.05M1M
Max output66K30K
Input $ / M tokens$0.30$1.25
Output $ / M tokens$2.50$2.50
Results tracked5446

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

Category by category

Coding Grok 4.20 (Non-Reasoning) leads

Gemini 2.5 Flash: 35.8 (#220), Grok 4.20 (Non-Reasoning): 42.1 (#112)

BenchmarkGemini 2.5 FlashGrok 4.20 (Non-Reasoning)
WeirdML41.9%52.3%
LMArena Coding14241459
ALE-Bench661.881,150
SWE-bench Verified (bash only)28.7%—
Aider Polyglot55.1%—
LMArena WebDev—1375

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

Gemini 2.5 Flash: 30.8 (#74), Grok 4.20 (Non-Reasoning): 34.4 (#46)

BenchmarkGemini 2.5 FlashGrok 4.20 (Non-Reasoning)
Terminal-Bench17.1%57.3%
Vending-Bench 2548.844,663
Berkeley Function Calling Leaderboard56.2%—
TheAgentCompany41.1%—
τ²-bench Banking—18%
BALROG33.5%—
LMArena Search—1189

Reasoning Grok 4.20 (Non-Reasoning) leads

Gemini 2.5 Flash: 18.1 (#286), Grok 4.20 (Non-Reasoning): 52.3 (#32)

BenchmarkGemini 2.5 FlashGrok 4.20 (Non-Reasoning)
ARC-AGI-22.5%65.1%
Kagi LLM Benchmark56.8%75%
ARC-AGI-133.3%89.5%
LMArena Hard Prompts14221451
DTBench76.5%90.1%
LMCA27.5%38.7%
Epoch Capabilities Index143.03151.98
ForecastBench60.661.4
SimpleBench41.2%—
NYT Connections (extended)—85.4%
CritPt1.1%—
Chess Puzzles—24%
EnigmaEval2.7%—
Thematic Generalization—63.8%

Math Grok 4.20 (Non-Reasoning) leads

Gemini 2.5 Flash: 39.9 (#98), Grok 4.20 (Non-Reasoning): 48.2 (#65)

BenchmarkGemini 2.5 FlashGrok 4.20 (Non-Reasoning)
OTIS Mock AIME 2024-202573.1%92.2%
LMArena Math14151455
FrontierMath (Tiers 1-3)—44.9%
FrontierMath Tier 4—17.1%
ProofBench—14%
Omni-MATH38.5%—
FrontierMath (Feb 2025 set)4.8%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Grok 4.20 (Non-Reasoning) leads

Gemini 2.5 Flash: 36.4 (#168), Grok 4.20 (Non-Reasoning): 52.8 (#60)

BenchmarkGemini 2.5 FlashGrok 4.20 (Non-Reasoning)
LMArena Expert14261439
GPQA Diamond—89.3%
Humanity's Last Exam12.1%—
SimpleQA Verified—30.2%
MMLU-Pro63.9%—
Confabulations16.8%—
Vectara Hallucination Rate7.8%—
GPQA (HELM)39%—

Multimodal Gemini 2.5 Flash leads

Gemini 2.5 Flash: 41.8 (#32), Grok 4.20 (Non-Reasoning): 33.3 (#98)

BenchmarkGemini 2.5 FlashGrok 4.20 (Non-Reasoning)
LMArena Vision12531263
GeoBench76%—
VPCT46.2%—
Blueprint-Bench 2—0%
LMArena Document—1416
SpatialViz-Bench36.9%—

Multilingual Grok 4.20 (Non-Reasoning) leads

Gemini 2.5 Flash: 52.3 (#88), Grok 4.20 (Non-Reasoning): 54.5 (#40)

BenchmarkGemini 2.5 FlashGrok 4.20 (Non-Reasoning)
LMArena Non-English14091441
LMArena Chinese14501481
LMArena French14331476
LMArena German14181465
LMArena Japanese14051449
LMArena Korean13851417
LMArena Russian14151458
LMArena Spanish14211443

Instruction Following Too close to call

Gemini 2.5 Flash: 75.7 (#54), Grok 4.20 (Non-Reasoning): 74.8 (#83)

BenchmarkGemini 2.5 FlashGrok 4.20 (Non-Reasoning)
LMArena Instruction Following14051420
IFEval89.8%—

Long Context Gemini 2.5 Flash leads

Gemini 2.5 Flash: 47.5 (#17), Grok 4.20 (Non-Reasoning): 45.5 (#34)

BenchmarkGemini 2.5 FlashGrok 4.20 (Non-Reasoning)
LMArena Longer Query14191437
Fiction.LiveBench77.8%—
CL-bench—22.2%
CL-bench Life—11.9%

Writing & Preference Grok 4.20 (Non-Reasoning) leads

Gemini 2.5 Flash: 53.8 (#157), Grok 4.20 (Non-Reasoning): 65.7 (#44)

BenchmarkGemini 2.5 FlashGrok 4.20 (Non-Reasoning)
LMArena Text14171451
LMArena Creative Writing14001438
EQ-Bench Creative Writing11371574
LMArena Multi-Turn14081456
Short-Story Creative Writing76.5%—
WildBench81.7%—

Frequently asked questions

Is Gemini 2.5 Flash better than Grok 4.20 (Non-Reasoning)?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 1.8× 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, Gemini 2.5 Flash or Grok 4.20 (Non-Reasoning)?

Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.

Is Gemini 2.5 Flash or Grok 4.20 (Non-Reasoning) better for coding?

Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 35.8 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Flash does, with 1.05M tokens against 1M.

How many benchmarks do Gemini 2.5 Flash and Grok 4.20 (Non-Reasoning) share?

31 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.

Related comparisons

Go deeper