Gemini 3.1 Pro Preview vs GPT-5.
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 | GPT-5 | Winner |
|---|---|---|---|
| League Score | 58.4 | 60.0 | GPT-5 |
| Coding (SWE-bench %) | 75.6 | 73.6 | Gemini 3.1 Pro Preview |
| Reasoning (GPQA %) | 94.3 | — | — |
| Context (tokens) | 1000000 | 400000 | Gemini 3.1 Pro Preview |
| Speed (tok/s) | — | — | — |
| Price (blended $/1M) | $4.50 | $3.44 | GPT-5 (cheaper) |
Tale of the tape
| Spec | Gemini 3.1 Pro Preview | GPT-5 |
|---|---|---|
| Maker | Google DeepMind | OpenAI |
| Released | Feb 19, 2026 | Aug 7, 2025 |
| League Score | 58 | 60 |
| Context | 1,000,000 tokens | 400,000 tokens |
| Max output | 65,536 | 128,000 |
| $/1M input | $2.00 | $1.25 |
| $/1M output | $12.00 | $10.00 |
| Weights | Closed | Closed |
| Speed | — | — |
Head-to-head benchmarks (shared only)
| Benchmark | Gemini 3.1 Pro Preview | GPT-5 |
|---|---|---|
| SWE-bench Verified | 75.6 | 73.6 |
Cost at three workloads
| Workload | Gemini 3.1 Pro Preview | GPT-5 |
|---|---|---|
| Light — 1M in / 250K out | $5.00 | $3.75 |
| Standard — 10M in / 2.5M out | $50.00 | $37.50 |
| Long-context — 50M in / 5M out | $160.00 | $112.50 |
The pick
Pick Gemini 3.1 Pro Preview if you need the bigger context window; coding is the priority.
Pick GPT-5 if you want the higher overall League Score; you want the lower running cost.
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 GPT-5?
GPT-5 leads on overall League Score, 60 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 GPT-5?
GPT-5 is cheaper: $3.44 vs $4.50 blended per 1M tokens (3:1 input/output mix) — about 1.3x less per token.
Which has the bigger context window, Gemini 3.1 Pro Preview or GPT-5?
Gemini 3.1 Pro Preview, with 1M of context against 400K for GPT-5.
Which is better for coding, Gemini 3.1 Pro Preview or GPT-5?
Gemini 3.1 Pro Preview scores higher on SWE-bench Verified, 75.6% vs 73.6% of real GitHub issues resolved.
Are Gemini 3.1 Pro Preview and GPT-5 open source?
Gemini 3.1 Pro Preview is closed weights — API access only; GPT-5 is closed weights — API access only.