See key specs and per-benchmark scores for each model/mode. Scroll horizontally for all columns. 当前对比 2 个模型的评测数据与核心参数。
Gemini 3.0 Flash
Google Deep Mind
Each axis is a category average, normalized to a 100-point radar.
Relative edge: Agent能力评测 +57.2 / Relative gap: none clear
Relative edge: none clear / Relative gap: Agent能力评测 -57.2
Method: for each model and benchmark, the chart first averages all scores in the current mode scope instead of taking the best score, then averages those benchmark scores within each category. Only benchmarks with at least two selected models scored are included; missing values are not counted as zero.
Best overall
Gemini 3.0 Flash · 65.08
Best single
Gemini 3.0 Flash · AIME2025 99.70
Modality coverage
Gemini 3.0 Flash · 4 modalities
Head to head
10
Benchmarks
8
Wins
2
Losses
+14.78
Average diff
Compare benchmark results across thinking modes and tool usage.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Complete scores for each model/mode across selected benchmarks.
10 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Gemini 3.0 Flash | Haiku 4.5 |
|---|---|---|
ARC-AGI-2 综合评估 | 33.60Thinking Enabled | 4.50Extended Thinking |
GPQA Diamond 综合评估 | 90.40Thinking Enabled | 73.30Extended Thinking |
HLE 综合评估 | 43.50Thinking Enabled ｜ Tools | 9.70Extended Thinking |
SWE-Bench Pro - Public 编程与软件工程 | 49.60Thinking Level · High ｜ Tools | 39.45Extended Thinking ｜ Tools |
SWE-bench Verified 编程与软件工程 | 68.70Thinking Enabled | 73.30128K ｜ Tools |
AIME2025 数学推理 | 99.70Thinking Enabled ｜ Tools | 96.30128K ｜ Tools |
4.20Standard Mode | 2.1032K | |
τ²-Bench Agent能力评测 | 90.20Thinking Enabled ｜ Tools | 33.00Standard Mode ｜ Tools |
Claw Bench OpenClaw智能体能力综合测评 | 85.70Thinking Enabled ｜ Tools | 89.40Thinking Enabled ｜ Tools |
Pinch Bench OpenClaw智能体能力综合测评 | 85.20Thinking Enabled ｜ Tools | 82.00Thinking Enabled ｜ Tools |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | Gemini 3.0 FlashGoogle Deep Mind | Haiku 4.5Anthropic |
|---|---|---|
Core specsRelease | 2025-12-17 | 2025-10-15 |
Context length | 2000K | 200K |
Max output | 65536 | 65536 |
MoE | No | No |
Supported modes | 常规模式（Non-Thinking Mode）思考模式（Thinking Mode）深度思考（Deeper Thinking Mode） | 常规模式（Non-Thinking Mode）思考模式（Thinking Mode） |
LicenseCode Open Source | Not provided | Not provided |
Weights Open Source | Not provided | Not provided |
Commercial use | 不开源 | 不开源 |
Modality supportText Input/Output | / | / |
Image Input/Output | / | / |
Audio Input/Output | / | Not provided |
Video Input/Output | / | Not provided |
ResourcesPaper / report | Gemini 3 Flash: frontier intelligence built for speed | Introducing Claude Haiku 4.5 |
DataLearner blog | Gemini 3 Flash：Google 在 12 月 17 日发布的新一代默认模型 | Anthropic发布Claude Haiku 4.5：一个不可忽视的低成本模型，1/3的价格，1.5倍的速度，但是有Claude Sonnet 4的水平！ |
Haiku 4.5
Anthropic
