Coding · Google DeepMind

Gemini 3 Flash Mini on SWE-bench Verified: score, rank and what it means

Gemini 3 Flash Mini scores 61.4 on SWE-bench Verified, placing it #292 of 600 models in the index. The benchmark average is 57.5 and the leader is GPT-5.2 Pro at 81.7.

Score
61.4
0–100 scale
Rank
#292
of 600
Percentile
51th
within the index
Benchmark avg
57.5
all models
Leader
81.7
GPT-5.2 Pro
Gap to leader
20.3
points

Score distribution

The chart shows the top 10 models on SWE-bench Verified, with Gemini 3 Flash Mini highlighted. Longer bars mean higher scores.

GPT-5.2 Pro 81.7
Claude Opus 4.5 Pro 81.1
GPT-5.2 Max 80.5
Claude Sonnet 4.5 Max 80.2
GPT-5.2 80.2
GPT-5.1 Pro 80.1
o4 Max 79.8
Claude Sonnet 4.5 Reasoning 79.6
Claude Opus 4.5 Max 79.5
Claude Opus 4.5 Reasoning 79.5

Top 10 leaderboard

#ModelProviderContextInput / 1MAvg score
1 GPT-5.2 Pro OpenAI 2000000 $21.32 89.6
2 Claude Opus 4.5 Pro Anthropic 200000 $20.98 89.1
3 GPT-5.2 Max OpenAI 1000000 $21.39 89.2
4 Claude Sonnet 4.5 Max Anthropic 1000000 $19.90 87.2
5 GPT-5.2 OpenAI 2000000 $19.71 88.0
6 GPT-5.1 Pro OpenAI 200000 $19.77 87.8
7 o4 Max OpenAI 2000000 $19.51 86.2
8 Claude Sonnet 4.5 Reasoning Anthropic 400000 $19.48 87.7
9 Claude Opus 4.5 Max Anthropic 1000000 $20.90 87.8
10 Claude Opus 4.5 Reasoning Anthropic 2000000 $20.91 88.2

What this score means

On SWE-bench Verified, Gemini 3 Flash Mini sits at #292 of 600. The leader, GPT-5.2 Pro, scores 81.7, so the gap to the top is 20.3 points. The median model in this index scores 61.0, which puts Gemini 3 Flash Mini above the midpoint.

Google DeepMind models average 66.4 on this benchmark. Gemini 3 Flash Mini is 5.0 points below that provider line, so it is a weaker result than the average Google DeepMind model.

Among multimodal models, the average is 66.4. Gemini 3 Flash Mini is 5.0 points below that group. This is the more useful comparison if you are shortlisting within the same tier rather than across the whole index.

Read a 61.4 as a relative signal, not an absolute guarantee. Benchmark scores depend on prompt format, evaluation harness and contamination controls. Use this page to narrow the shortlist, then test the model on your own data.

Price context

At $10.71 per million input tokens, Gemini 3 Flash Mini is above the median input price of $4.00 across the 600 models scored on SWE-bench Verified. The models immediately around it in the ranking are shown below so you can compare score and price together.

ModelProviderContextInput / 1MAvg score
Fusion Reasoning OpenRouter 65536 $8.59 72.2
GLM-4.5 Base Zhipu AI 32768 $3.99 74.9
Llama 3 Novita Chat Novita AI 65536 $3.50 74.2
Mistral Small 3 Chat Mistral AI 200000 $3.54 73.7
Gemini 3 Flash Mini Google DeepMind 200000 $10.71 76.0
Llama 3 Anyscale Instruct Anyscale 200000 $3.91 75.7
Mixtral Base Mistral AI 65536 $2.95 71.1

Other benchmarks for Gemini 3 Flash Mini

BenchmarkScoreRankPercentileRelative
MMLU-Pro 78.8 216 64th
GPQA Diamond 73.8 174 71th
HumanEval 80.1 229 62th
MATH-500 78.9 237 61th
AIME 2025 74.3 169 72th
LiveCodeBench 69.1 206 66th
IFEval 83.6 222 63th
TruthfulQA 79.8 186 69th
HellaSwag 84.1 275 54th
MMMU 72.6 229 62th
Arena Elo 1406.3 191 68th

FAQ

What score does Gemini 3 Flash Mini get on SWE-bench Verified?

Gemini 3 Flash Mini scores 61.4 on SWE-bench Verified in this index. The benchmark average is 57.5 and the top score is 81.7.

How does Gemini 3 Flash Mini rank on SWE-bench Verified?

It ranks #292 of 600 models, in the 51st percentile. The leader is GPT-5.2 Pro at 81.7.

Is Gemini 3 Flash Mini good at SWE-bench Verified?

Yes, relative to the index: it is above the median and inside the top half of scores. The result should be read alongside its price and context window.

How is the SWE-bench Verified score calculated?

SWE-bench Verified is a coding benchmark. Scores in this index are modelled estimates on a 0–100 scale (or Elo for Arena), derived from capability tier and benchmark difficulty. They are not official leaderboard results.

What does Gemini 3 Flash Mini cost?

Gemini 3 Flash Mini costs $10.71 per million input tokens and $48.11 per million output tokens.

Related