The LLM benchmark aggregator.

Gemini 2.0 Flash

Google

Strongest in Safe-prompt compliance (#48 of 82), weakest in Toxicity avoidance (#199 of 268). Above par in 8 of 23 scopes. Among the models it meets almost everywhere, it finishes behind GPT-5 and O3 and ahead of Gemma 4 31B and Claude 3.5 Haiku.

§ 1 · Profile

What it is good at

Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.

Coding45.4−20.8#123/1791/6

Agentic coding44.9−22#119/1731/5

Knowledge48−14.5#135/1971/3

Academic knowledge45.2−18.7#96/1231/1

Safety51.5−9.9#143/3292/3

Safe-prompt compliance52.6−7.8#48/821/1

Jailbreak resistance57.3−7.7#77/2681/1

Fairness50.2−19.8#111/2922/2

Harm refusal52.1−9.4#120/2922/2

Secure code45.8−20.4#189/2701/1

Toxicity avoidance49.7−9.3#199/2681/1

Core abilities44.9−20.4#144/1991/4

General intelligence42.7−26.7#138/1781/3

Professional45.6−16.8#148/1941/2

Legal50.1−15.8#89/1731/1

Medical48.9−17.6#96/1491/1

Finance40.7−21.7#136/1621/1

Human preference52.8−16#167/3541/1

Reasoning38.6−26.8#178/1953/5

Science42.4−21.1#95/1221/1

Mathematics40.3−23.5#119/1521/2

Reasoning35.2−33.8#140/1472/3

§ 2 · Head to head

What it beats, and what beats it

The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for Gemini 2.0 Flash, left for the other.

Jamba 1.6 Miniwon 15 · lost 0

Jamba 1.6 Largewon 15 · lost 0

Command R+won 16 · lost 0

Gemini 1.5 Flashwon 16 · lost 1

Mistral Medium 3.5won 13 · lost 2

Llama 4 Scout Instructwon 18 · lost 3

Command Awon 17 · lost 4

Gemini 1.5 Prowon 15 · lost 4

Llama 3.3 70B Instructwon 13 · lost 4

GPT-4.1 nanowon 17 · lost 6

Magistral Small 1.2won 11 · lost 4

GPT-4o miniwon 16 · lost 6

Claude 3.5 Haikuwon 11 · lost 7

Gemma 4 31Bwon 11 · lost 7

GPT OSS 20Bwon 10 · lost 10

GPT-5.4 nanowon 8 · lost 9

Grok 4.3won 9 · lost 11

Ling 3.0 Flashwon 7 · lost 9

Llama 4 Maverick Instructwon 10 · lost 13

Llama 3.1 405B Instructwon 6 · lost 8

GPT-4owon 9 · lost 12

DeepSeek V3.1won 6 · lost 9

Grok 4.1 Fastwon 8 · lost 12

GPT-5 nanowon 8 · lost 13

Gemini 3.5 Flash-Litewon 6 · lost 10

NVIDIA Nemotron 3 Ultra 550B A55Bwon 8 · lost 14

Qwen3.6 Pluswon 5 · lost 9

GPT OSS 120Bwon 8 · lost 15

Claude Haiku 4.5won 7 · lost 14

Kimi K2.5won 7 · lost 15

MiMo V2.5 Prowon 6 · lost 13

Gemini 3.1 Flash-Litewon 5 · lost 11

Grok 4.20won 5 · lost 11

GLM-4.6won 6 · lost 15

Qwen3.7 Maxwon 6 · lost 15

MiniMax M3won 6 · lost 16

DeepSeek V4 Flashwon 6 · lost 16

Qwen3 Maxwon 4 · lost 11

Gemini 3 Flashwon 4 · lost 11

DeepSeek V3won 6 · lost 17

GPT-5.4 miniwon 4 · lost 12

GPT-6 Lunawon 5 · lost 15

Kimi K2.6won 5 · lost 15

DeepSeek R1won 5 · lost 17

Inklingwon 5 · lost 17

DeepSeek V4 Prowon 5 · lost 17

MiMo V2.6 Flashwon 4 · lost 14

GPT-4.1 miniwon 5 · lost 18

Grok 3won 5 · lost 18

GLM-4.5won 4 · lost 15

MiniMax M2.7won 4 · lost 15

Mistral Large 4won 4 · lost 15

GPT-6 Solwon 4 · lost 15

GPT-4 Turbowon 3 · lost 12

O1 Miniwon 3 · lost 12

GLM-4.7won 3 · lost 12

Kimi K2 Thinkingwon 4 · lost 16

Gemini 3.5 Flashwon 4 · lost 17

Gemini 3.6 Flashwon 4 · lost 17

DeepSeek V3.2won 4 · lost 18

GLM-5.3 Flashwon 4 · lost 18

GLM-5.2won 4 · lost 18

Grok 4 Fastwon 3 · lost 14

Mistral Large 3won 3 · lost 14

Claude Opus 4.5won 3 · lost 14

Gemini 2.5 Flashwon 4 · lost 19

Grok 4won 4 · lost 19

GLM-5.1won 3 · lost 17

Qwen3.5 Flashwon 2 · lost 12

Claude Haiku 5.5won 2 · lost 12

GPT-5.6 Lunawon 3 · lost 19

MiniMax M2.1won 2 · lost 13

GPT-6 Astrawon 2 · lost 13

GPT-5 miniwon 3 · lost 20

Gemini 2.5 Prowon 3 · lost 20

Inkling Smallwon 2 · lost 14

Qwen3.8 27Bwon 2 · lost 14

Gemini 2.5 Flash-Litewon 2 · lost 15

MiniMax M2.5won 2 · lost 15

GLM-5won 2 · lost 15

MiMo V2.6 Prowon 2 · lost 17

Claude 3.5 Sonnetwon 2 · lost 18

Gemini 3 Prowon 2 · lost 18

O3 Miniwon 2 · lost 19

Claude 3.7 Sonnetwon 2 · lost 19

GPT-5.6 Terrawon 2 · lost 20

GPT-5.5won 2 · lost 20

Qwen3.8 Maxwon 2 · lost 20

GPT-5.6 Solwon 2 · lost 20

Gemini 3.8 Flashwon 2 · lost 20

O4 Miniwon 2 · lost 21

Kimi K2won 2 · lost 21

GPT-6.1 Solwon 1 · lost 13

Gemini 4 Argonwon 1 · lost 13

Gemini 3.1 Prowon 1 · lost 15

Claude Sonnet 4.6won 1 · lost 18

Grok 3 Miniwon 1 · lost 19

Claude Opus 4.6won 1 · lost 19

GPT-5.1won 1 · lost 20

Claude Opus 5won 1 · lost 20

Grok 4.6won 1 · lost 21

Grok 4.5won 1 · lost 21

GPT-5.4won 1 · lost 21

Claude Sonnet 4won 1 · lost 22

GPT-4.1won 1 · lost 22

Qwen3 235B A22B Instructwon 1 · lost 22

Claude Sonnet 4.5won 1 · lost 22

Claude Sonnet 5.5won 0 · lost 14

Muse Spark 1.2won 0 · lost 14

DeepSeek V4.1 Flashwon 0 · lost 15

Gemini 3.7 Flashwon 0 · lost 15

GLM-5.3won 0 · lost 16

Kimi K3won 0 · lost 16

Claude Fable 5.1won 0 · lost 16

Claude Fable 5won 0 · lost 16

Grok 4.7won 0 · lost 19

Muse Spark 1.1won 0 · lost 20

Claude Opus 5.5won 0 · lost 20

O1won 0 · lost 21

Claude Sonnet 5won 0 · lost 21

GPT-5.2won 0 · lost 22

Claude Opus 4.8won 0 · lost 22

Claude Opus 4.7won 0 · lost 22

Claude Opus 4won 0 · lost 23

O3won 0 · lost 23

GPT-5won 0 · lost 23

§ 3 · Sources

Where the numbers come from

8 publications, 24 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-11-10

LMArena Text 1360

ARC-AGI-2 ↗1 measureread 2026-11-10

ARC-AGI-2 1.3%

Aider polyglot ↗1 measureread 2026-11-10

Aider polyglot 22.2%

Kagi LLM Benchmark ↗1 measureread 2026-11-10

Kagi LLM Benchmark 37.8%

SimpleBench ↗1 measureread 2026-11-10

SimpleBench 18.9%

Vals.ai ↗8 measuresread 2026-11-10

Vals · LegalBench 78.36%Vals · CorpFin 33.72%Vals · TaxEval 65.25%Vals · MortgageTax 59.66%Vals · MedQA 81.47%Vals · GPQA Diamond 65.15%Vals · MMLU Pro 77.38%Vals · AIME 29.79%

HELM Safety ↗5 measuresread 2026-11-10

HELM Safety · HarmBench 66.2%HELM Safety · SimpleSafetyTests 98.5%HELM Safety · Anthropic Red Team 99.4%HELM Safety · BBQ 95.4%HELM Safety · XSTest 95.3%

Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-11-10

Enkrypt · Jailbreak risk 6.7%Enkrypt · Harmful content risk 36.1%Enkrypt · CBRN risk 6.7%Enkrypt · Toxicity risk 6.4%Enkrypt · Bias risk 86.3%Enkrypt · Insecure code risk 41.8%

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=gemini-2-0-flash)](https://publicai.io/model-index/m/gemini-2-0-flash)