Compare · ModelsLive · 2 picked · head to head
Step 3.5 Flash vs Gemini 3.1 Pro Preview
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemini 3.1 Pro Preview wins on 4/4 benchmarks
Gemini 3.1 Pro Preview wins 4 of 4 shared benchmarks. Leads in speed · arena.
Category leads
speed·Gemini 3.1 Pro Previewarena·Gemini 3.1 Pro Preview
Hype vs Reality
Attention vs performance
Step 3.5 Flash
#9 by perf·#11 by attention
Gemini 3.1 Pro Preview
#38 by perf·no signal
Best value
Step 3.5 Flash
44.4x better value than Gemini 3.1 Pro Preview
Step 3.5 Flash
384.5 pts/$
$0.20/M
Gemini 3.1 Pro Preview
8.7 pts/$
$7.00/M
Vendor risk
Mixed exposure
One or more vendors flagged
StepFun
$5.0B·Tier 1
Google DeepMind
$4.00T·Tier 1
Head to head
4 benchmarks · 2 models
Step 3.5 FlashGemini 3.1 Pro Preview
Artificial Analysis · Agentic Index
Gemini 3.1 Pro Preview leads by +7.1
Artificial Analysis Agentic Index · a composite score measuring how well a model performs in agentic workflows · multi-step tool use, planning, error recovery, and autonomous task completion. Aggregates results from multiple agentic benchmarks including SWE-bench, tool-use tests, and planning evaluations. The canonical single-number metric for "how good is this model as an agent?"
Step 3.5 Flash
52.0
Gemini 3.1 Pro Preview
59.1
Artificial Analysis · Coding Index
Gemini 3.1 Pro Preview leads by +23.9
Artificial Analysis Coding Index · a composite score that aggregates performance across multiple coding benchmarks into a single index. Tracks code generation quality, debugging ability, multi-language competence, and real-world software engineering tasks. Used by Artificial Analysis to rank model coding capability in a normalized, comparable format. Useful for developers choosing between models for coding-heavy workloads.
Step 3.5 Flash
31.6
Gemini 3.1 Pro Preview
55.5
Artificial Analysis · Quality Index
Gemini 3.1 Pro Preview leads by +19.4
Step 3.5 Flash
37.8
Gemini 3.1 Pro Preview
57.2
Chatbot Arena Elo · Overall
Gemini 3.1 Pro Preview leads by +101.2
Step 3.5 Flash
1391.4
Gemini 3.1 Pro Preview
1492.6
Full benchmark table
| Benchmark | Step 3.5 Flash | Gemini 3.1 Pro Preview |
|---|---|---|
Artificial Analysis · Agentic Index Artificial Analysis Agentic Index · a composite score measuring how well a model performs in agentic workflows · multi-step tool use, planning, error recovery, and autonomous task completion. Aggregates results from multiple agentic benchmarks including SWE-bench, tool-use tests, and planning evaluations. The canonical single-number metric for "how good is this model as an agent?" | 52.0 | 59.1 |
Artificial Analysis · Coding Index Artificial Analysis Coding Index · a composite score that aggregates performance across multiple coding benchmarks into a single index. Tracks code generation quality, debugging ability, multi-language competence, and real-world software engineering tasks. Used by Artificial Analysis to rank model coding capability in a normalized, comparable format. Useful for developers choosing between models for coding-heavy workloads. | 31.6 | 55.5 |
Artificial Analysis · Quality Index | 37.8 | 57.2 |
Chatbot Arena Elo · Overall | 1391.4 | 1492.6 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.10 | $0.30 | 262K tokens (~131 books) | $1.50 | |
| $2.00 | $12.00 | 1.0M tokens (~524 books) | $45.00 |