Noometry

Google, proprietary

Gemini 2.0 Flash (Feb 2025)

Gemini 2.0 Flash (Feb 2025) by Google ranks 228th of 354 ranked models on the Noometry Index as of October 2026, with a score of 35.1. Its strongest category is multimodal, where it ranks 79th.

Last verified

Noometry rank
#228 of 354
Index score
35.1
Evidence
Confirmed 54 results
Provider
Google
Released
December 6, 2024
Weights
Proprietary
Reasoning
Unknown
Context window
—
Max output
—
Input price
Not listed
Output price
Not listed
Blended price
Not listed
Output speed
92 tokens/s Kagi
Value
Not ranked
Knowledge cutoff
Unknown

Category scores

Each category score combines every public result we have in that category.

  1. Coding 28.4
  2. Agentic & Tool Use 28.1
  3. Reasoning 15.2
  4. Math 37.9
  5. Knowledge 32.0
  6. Multimodal 36.5
  7. Multilingual 47.4
  8. Instruction Following 74.4
  9. Long Context 38.1
  10. Writing & Preference 49.5
CategoryScoreRankResults
Coding28.4#3158
Agentic & Tool Use28.1#921
Reasoning15.2#3188
Math37.9#1465
Knowledge32.0#2136
Multimodal36.5#792
Multilingual47.4#1491
Instruction Following74.4#973
Long Context38.1#2032
Writing & Preference49.5#1907

Strengths and weaknesses

Categories where Gemini 2.0 Flash (Feb 2025) places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Instruction Following74.4+3.1#97 of 305, top 32%
Math37.9+1.3#146 of 327, top 45%
Multilingual47.4−0.0#149 of 297, top 51%

Weakest categories

CategoryScorevs medianRank
Coding28.4−10.3#315 of 340, top 93%
Reasoning15.2−8.4#318 of 350, top 91%
Long Context38.1−2.8#203 of 296, top 69%

Closest competitors

The models ranked just above and below Gemini 2.0 Flash (Feb 2025). When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
Llama 3.1 Tulu 3 8b#22435.7——Compare
Qwen3 14B#22535.5$0.6179Compare
DeepSeek-R1-Distill-Qwen-32B#22635.5——Compare
Magistral Medium#22735.2$2.750Compare
C4ai Aya Expanse 8b#22934.9——Compare
Qwen Max#23034.7$2.80—Compare
Claude 3.5 Sonnet#23134.6——Compare
Qwen3 Coder Next#23234.3$0.29—Compare

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

Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

Coding

BenchmarkScorePositionSettingSourceDate
SWE-bench Verified (bash only)13.5%#37 of 39, top 95%SWE-bench2025-07-26
Aider Polyglot18.2%Epoch AI
Aider Polyglot22.2%Epoch AI
Aider Polyglot38.2%#29 of 44, top 66%Epoch AI
WeirdML25.8%#98 of 119, top 83%Epoch AI
BigCodeBench Instruct45.9%#16 of 64, top 25%BigCodeBench2025-02-05
LiveBench Coding53.5%Epoch AI
LiveBench Coding53.9%Epoch AI
LiveBench Coding54.4%Epoch AI
LiveBench Coding63.4%#13 of 39, top 34%Epoch AI
LMArena Coding1350#173 of 294, top 59%LMArena2026-10-08
BigCodeBench Complete59.9%#4 of 66, top 7%BigCodeBench2025-02-05
CadEval30%#11 of 14, top 79%Epoch AI

Agentic & Tool Use

BenchmarkScorePositionSettingSourceDate
TheAgentCompany11.4%#7 of 14, top 50%Epoch AI

Reasoning

BenchmarkScorePositionSettingSourceDate
ARC-AGI-21.3%#67 of 83, top 81%Epoch AI
SimpleBench31.1%#59 of 77, top 77%Epoch AI
SimpleBench30.7%Epoch AI
SimpleBench18.9%Epoch AI
Kagi LLM Benchmark37.8%#82 of 99, top 83%Kagi LLM Benchmark
EnigmaEval0.6%Epoch AI
EnigmaEval1.1%#31 of 38, top 82%Epoch AI
LiveBench Reasoning55.3%Epoch AI
LiveBench Reasoning59.1%Epoch AI
LiveBench Reasoning57%Epoch AI
LiveBench Reasoning78.2%#8 of 39, top 21%Epoch AI
LMArena Hard Prompts1346#163 of 297, top 55%LMArena2026-10-08
DTBench63.2%#105 of 151, top 70%Epoch AI
LiveBench Data Analysis67.5%Epoch AI
LiveBench Data Analysis69.4%#6 of 39, top 16%Epoch AI
LiveBench Data Analysis63.2%Epoch AI
LiveBench Data Analysis61.7%Epoch AI
Epoch Capabilities Index134.69Epoch AI2025-02-05
Epoch Capabilities Index135.36#125 of 213, top 59%Epoch AI2025-01-21
Epoch Capabilities Index134.69Epoch AI2024-12-11
LiveBench61.5%Epoch AI
LiveBench66.9%#9 of 39, top 24%Epoch AI
LiveBench64.1%Epoch AI
LiveBench59.3%Epoch AI

Math

BenchmarkScorePositionSettingSourceDate
OTIS Mock AIME 2024-202557.8%#106 of 173, top 62%Epoch AI2025-03-07
OTIS Mock AIME 2024-202531.1%Epoch AI2025-02-25
Omni-MATH45.9%#22 of 57, top 39%HELM Capabilities
LiveBench Math65.6%Epoch AI
LiveBench Math75.8%#8 of 39, top 21%Epoch AI
LiveBench Math72.4%Epoch AI
LiveBench Math60.4%Epoch AI
LMArena Math1352#165 of 285, top 58%LMArena2026-10-08
MATH Level 582.2%#24 of 79, top 31%Epoch AI2025-02-06
FrontierMath (Feb 2025 set)1.7%#56 of 68, top 83%Epoch AI2025-03-09

Knowledge

BenchmarkScorePositionSettingSourceDate
GPQA Diamond64.1%#110 of 186, top 60%Epoch AI2025-02-06
GPQA Diamond57.1%Epoch AI2025-02-06
Humanity's Last Exam6.6%#32 of 41, top 79%Epoch AI
MMLU-Pro73.7%#30 of 58, top 52%HELM Capabilities
Confabulations (lower is better)26.9%Lech Mazur benchmarks
Confabulations (lower is better)12.4%#8 of 51, top 16%Lech Mazur benchmarks
GPQA (HELM)55.6%#27 of 57, top 48%HELM Capabilities
LMArena Expert1339#158 of 273, top 58%LMArena2026-10-08
MMLU79.7%#19 of 81, top 24%Epoch AI

Multimodal

BenchmarkScorePositionSettingSourceDate
LMArena Vision1158#97 of 122, top 80%LMArena2026-10-09
GeoBench77%#6 of 25, top 24%Epoch AI

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1342#149 of 297, top 51%LMArena2026-10-08
LMArena Chinese1373#154 of 285, top 55%LMArena2026-10-08
LMArena French1391#125 of 223, top 57%LMArena2026-10-08
LMArena German1353#127 of 231, top 55%LMArena2026-10-08
LMArena Japanese1294#124 of 211, top 59%LMArena2026-10-08
LMArena Korean1313#123 of 213, top 58%LMArena2026-10-08
LMArena Russian1351#147 of 283, top 52%LMArena2026-10-08
LMArena Spanish1363#134 of 226, top 60%LMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LiveBench Instruction Following85.8%#2 of 39, top 6%Epoch AI
LiveBench Instruction Following81.9%Epoch AI
LiveBench Instruction Following77.3%Epoch AI
LiveBench Instruction Following82.5%Epoch AI
IFEval84.1%#22 of 57, top 39%HELM Capabilities
LMArena Instruction Following1336#152 of 298, top 52%LMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
Fiction.LiveBench61.1%#29 of 47, top 62%Epoch AI
Fiction.LiveBench52.8%Epoch AI
LMArena Longer Query1344#155 of 291, top 54%LMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1354#155 of 297, top 53%LMArena2026-10-08
LMArena Creative Writing1340#138 of 295, top 47%LMArena2026-10-08
Short-Story Creative Writing71.5%Epoch AI
Short-Story Creative Writing73.8%#26 of 39, top 67%Epoch AI
EQ-Bench Creative Writing1128#91 of 115, top 80%EQ-Bench
WildBench80%#30 of 57, top 53%HELM Capabilities
LMArena Multi-Turn1350#155 of 295, top 53%LMArena2026-10-08
LiveBench Language40.7%Epoch AI
LiveBench Language51.3%#9 of 39, top 24%Epoch AI
LiveBench Language38.2%Epoch AI
LiveBench Language42.2%Epoch AI

Compare Gemini 2.0 Flash (Feb 2025)

Other Google models

Frequently asked questions

How good is Gemini 2.0 Flash (Feb 2025)?

Gemini 2.0 Flash (Feb 2025) by Google ranks 228th of 354 ranked models on the Noometry Index as of October 2026, with a score of 35.1. Its strongest category is multimodal, where it ranks 79th.

Is Gemini 2.0 Flash (Feb 2025) open source?

No. Gemini 2.0 Flash (Feb 2025) is proprietary and available only through Google's API and partner platforms.

How fast is Gemini 2.0 Flash (Feb 2025)?

Gemini 2.0 Flash (Feb 2025) generated about 92 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.

What are Gemini 2.0 Flash (Feb 2025)'s strengths and weaknesses?

Relative to other ranked models, Gemini 2.0 Flash (Feb 2025) places best in instruction following, math, multilingual and lowest in coding, reasoning, long context.

What is Gemini 2.0 Flash (Feb 2025) best at?

Its best category is multimodal, where it ranks 79th on Noometry.