Compare / Gemini 2.5 Pro vs GPT-5.4 Mini
Gemini 2.5 Pro vs GPT-5.4 Mini
Which is cheaper, which is more capable, and which does better at each kind of work, from 21 results on 3 sources that measured both models.
Gemini 2.5 Pro or GPT-5.4 Mini? The short answer
- GPT-5.4 Mini is cheaper: $1.69 against $3.44 per million tokens, 2.0 times less.
- GPT-5.4 Mini scores higher on the Artificial Analysis Intelligence Index: 24.1 against 16.1.
- On our business benchmarks, Gemini 2.5 Pro ranks higher for writing and sticking to the facts.
- On our business benchmarks, GPT-5.4 Mini ranks higher for agents and tool use and reasoning and knowledge.
At a glance
| Gemini 2.5 Pro | GPT-5.4 Mini | |
|---|---|---|
| Price per million tokens | $1.25 in · $10.00 out | $0.75 in · $4.50 out |
| Blended (3 in : 1 out) | $3.44 | $1.69 |
| Cheapest host, blended | $1.72 (Google AI Studio) | $0.84 (OpenAI) |
| Intelligence Index | 16.1 | 24.1 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | – |
| Context window | 1,048,576 tokens | 400,000 tokens |
| Weights | Closed | Closed |
| Developer based in | the US | the US |
Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.
Which is better for what
Each model's rank among models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.
| Use case | Gemini 2.5 Pro | GPT-5.4 Mini |
|---|---|---|
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 109 of 161 | 53 of 161 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 92 of 195 | 67 of 195 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 42 of 187 | 55 of 187 |
| Sticking to the factsSummarising without inventing things, and factual answers | 38 of 153 | 67 of 153 |
| Speed under pressureGood decisions against a real clock (fast chess) | not measured | 11 of 21 |
Every shared result
| Benchmark | Metric | Gemini 2.5 Pro | GPT-5.4 Mini |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,462 | 1,447 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,437 | 1,460 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,443 | 1,402 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,458 | 1,480 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,438 | 1,434 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,446 | 1,447 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,445 | 1,424 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 33.3 | 56.1 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 16.1 | 24.1 |
| Artificial Analysisreported | GPQA Diamond% of questions | 84.4% | 87.5% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 22.5% | 28.1% |
| Artificial Analysisreported | IFBench% of instructions | 48.7% | 73.3% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 69.0% | 77.0% |
| Artificial Analysisreported | SciCode% of problems | 46.3% | 52.1% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 28.5% | 59.2% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 0.0% | 2.0% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 26.5% | 52.3% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 9.7% | 25.6% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 54.1% | 83.3% |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 99.1% | 100.0% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 7.0% | 5.5% |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.
Quick answers
Is Gemini 2.5 Pro better than GPT-5.4 Mini?
It depends on the task. Among models available today, on our benchmarks and licensed sources, Gemini 2.5 Pro ranks higher for writing and sticking to the facts; GPT-5.4 Mini ranks higher for agents and tool use and reasoning and knowledge.
Which is cheaper, Gemini 2.5 Pro or GPT-5.4 Mini?
GPT-5.4 Mini costs $1.69 per million tokens (three input to one output), against $3.44 for Gemini 2.5 Pro.
Run Gemini 2.5 Pro and GPT-5.4 Mini on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.