GPT-5.4 minivsGemini 3.0 Flash
Across 8 shared benchmarks, Gemini 3.0 Flash leads overall: GPT-5.4 mini wins 2, Gemini 3.0 Flash wins 6, with 0 ties and an average score difference of -3.05.
GPT-5.4 mini
OpenAI · 2026-03-17 · Reasoning model
Gemini 3.0 Flash
Google Deep Mind · 2025-12-17 · Chat model
GPT-5.4 mini2 wins(25%)(75%)6 winsGemini 3.0 Flash
Benchmark scores
Grouped by capability, sorted by largest gap within each. 8 shared benchmarks.
General Knowledge
Gemini 3.0 Flash 3/3| Benchmark | GPT-5.4 mini | Gemini 3.0 Flash | Diff |
|---|---|---|---|
| LiveBench | 36.95112 / 115Normal (No Tools) | 56.3579 / 115Normal (No Tools) | -19.40 |
| GPQA Diamond | 8835 / 187极高强度思考（无工具） | 90.4019 / 187 | -2.40 |
| HLE | 41.5057 / 172极高强度思考（工具） | 43.5047 / 172 | -2 |
AI Agent - Tool Usage
Even 2/2| Benchmark | GPT-5.4 mini | Gemini 3.0 Flash | Diff |
|---|---|---|---|
| Terminal Bench 2.0 | 6019 / 47极高强度思考（工具） | 47.6038 / 47 | +12.40 |
| MCP-Atlas | 56.7024 / 27极高强度思考（工具） | 6220 / 27Normal (With Tools) | -5.30 |
Claw-style Agent Evaluation
Gemini 3.0 Flash 1/1| Benchmark | GPT-5.4 mini | Gemini 3.0 Flash | Diff |
|---|---|---|---|
| Claw Bench | 75.3025 / 29Thinking (With Tools) | 85.7015 / 29Thinking (With Tools) | -10.40 |
Coding and Software Engineer
GPT-5.4 mini 1/1| Benchmark | GPT-5.4 mini | Gemini 3.0 Flash | Diff |
|---|---|---|---|
| SWE-Bench Pro - Public | 54.4029 / 54极高强度思考（工具） | 49.6042 / 54Thinking High (With Tools) | +4.80 |
Math and Reasoning
Gemini 3.0 Flash 1/1| Benchmark | GPT-5.4 mini | Gemini 3.0 Flash | Diff |
|---|---|---|---|
| FrontierMath - Tier 4 | 2.1056 / 80Thinking High (No Tools) | 4.2040 / 80Normal (No Tools) | -2.10 |
Specs
| Field | GPT-5.4 mini | Gemini 3.0 Flash |
|---|---|---|
| Publisher | OpenAI | Google Deep Mind |
| Release date | 2026-03-17 | 2025-12-17 |
| Model type | Reasoning model | Chat model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 400K | 2000K |
| Max output | 128K | 64K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | GPT-5.4 mini | Gemini 3.0 Flash |
|---|---|---|
| Text input | $0.75 / 1M tokens | $0.5 / 1M tokens |
| Text output | $4.5 / 1M tokens | $3 / 1M tokens |
| Cache read | $4.5 / 1M tokens | Not public |
| Cache write | $0.075 / 1M tokens | Not public |
Summary
- GPT-5.4 minileads in:Coding and Software Engineer (1/1)
- Gemini 3.0 Flashleads in:General Knowledge (3/3), Claw-style Agent Evaluation (1/1), Math and Reasoning (1/1)
- Tied in:AI Agent - Tool Usage
On average across the 8 shared benchmarks, Gemini 3.0 Flash scores 3.05 higher.
Largest single-benchmark gap: LiveBench — GPT-5.4 mini 36.95 vs Gemini 3.0 Flash 56.35 (-19.40).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.