Gemini 3.1 Pro Preview vs Qwen3.5-397B-A17B.
Verdict by category, tale of the tape, shared benchmarks only, and cost at three workloads — all from the tracked data.
Verdict by category
| Category | Gemini 3.1 Pro Preview | Qwen3.5-397B-A17B | Winner |
|---|---|---|---|
| League Score | 58.4 | 60.7 | Qwen3.5-397B-A17B |
| Coding (SWE-bench %) | 75.6 | 76.2 | Qwen3.5-397B-A17B |
| Reasoning (GPQA %) | 94.3 | 88.4 | Gemini 3.1 Pro Preview |
| Context (tokens) | 1000000 | 262144 | Gemini 3.1 Pro Preview |
| Speed (tok/s) | — | — | — |
Tale of the tape
| Spec | Gemini 3.1 Pro Preview | Qwen3.5-397B-A17B |
|---|---|---|
| Maker | Google DeepMind | Alibaba Qwen |
| Released | Feb 19, 2026 | Feb 16, 2026 |
| League Score | 58 | 61 |
| Context | 1,000,000 tokens | 262,144 tokens |
| Max output | 65,536 | — |
| $/1M input | $2.00 | — |
| $/1M output | $12.00 | — |
| Weights | Closed | Open |
| Speed | — | — |
Head-to-head benchmarks (shared only)
| Benchmark | Gemini 3.1 Pro Preview | Qwen3.5-397B-A17B |
|---|---|---|
| GPQA Diamond | 94.3 | 88.4 |
| SWE-bench Verified | 75.6 | 76.2 |
Cost at three workloads
| Workload | Gemini 3.1 Pro Preview | Qwen3.5-397B-A17B |
|---|---|---|
| Light — 1M in / 250K out | $5.00 | — |
| Standard — 10M in / 2.5M out | $50.00 | — |
| Long-context — 50M in / 5M out | $160.00 | — |
The pick
Pick Gemini 3.1 Pro Preview if you need the bigger context window.
Pick Qwen3.5-397B-A17B if you want the higher overall League Score; you want downloadable weights / self-hosting; coding is the priority.
All figures from the model database — sources and dates on each model page. Cost your own workload or compare a different pair.
Frequently asked questions
Which is better overall, Gemini 3.1 Pro Preview or Qwen3.5-397B-A17B?
Qwen3.5-397B-A17B leads on overall League Score, 61 to 58 — a gap of 2 points on a composite of sourced benchmarks. That is overall form, not every category: check the per-category verdicts before choosing.
Which is cheaper, Gemini 3.1 Pro Preview or Qwen3.5-397B-A17B?
Only Gemini 3.1 Pro Preview has published API pricing in our database ($4.50 blended per 1M tokens); Qwen3.5-397B-A17B has no tracked API price, so a like-for-like cost verdict is not possible.
Which has the bigger context window, Gemini 3.1 Pro Preview or Qwen3.5-397B-A17B?
Gemini 3.1 Pro Preview, with 1M of context against 262.1K for Qwen3.5-397B-A17B.
Which is better for coding, Gemini 3.1 Pro Preview or Qwen3.5-397B-A17B?
Qwen3.5-397B-A17B scores higher on SWE-bench Verified, 76.2% vs 75.6% of real GitHub issues resolved.
Which is better at reasoning, Gemini 3.1 Pro Preview or Qwen3.5-397B-A17B?
Gemini 3.1 Pro Preview leads on GPQA Diamond, 94.3% vs 88.4% on graduate-level science questions.
Are Gemini 3.1 Pro Preview and Qwen3.5-397B-A17B open source?
Gemini 3.1 Pro Preview is closed weights — API access only; Qwen3.5-397B-A17B is open weights — it can be downloaded and self-hosted.