Head to head
GPT-6.1 Sol vs GPT-6.2 Sol.
Verdict by category, tale of the tape, shared benchmarks only, and cost at three workloads — all from the tracked data.
Verdict by category
| Category | GPT-6.1 Sol | GPT-6.2 Sol | Winner |
|---|---|---|---|
| League Score | 88.7 | 89.5 | GPT-6.2 Sol |
| Coding (SWE-bench %) | — | — | — |
| Reasoning (GPQA %) | — | 96.0 | — |
| Context (tokens) | 1050000 | 1050000 | Draw |
| Speed (tok/s) | — | — | — |
| Price (blended $/1M) | $4.00 | $4.00 | GPT-6.2 Sol (cheaper) |
Tale of the tape
| Spec | GPT-6.1 Sol | GPT-6.2 Sol |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Released | Sep 29, 2026 | Nov 17, 2026 |
| League Score | 89 | 90 |
| Context | 1,050,000 tokens | 1,050,000 tokens |
| Max output | 128,000 | 128,000 |
| $/1M input | $2.00 | $2.00 |
| $/1M output | $10.00 | $10.00 |
| Weights | Closed | Closed |
| Speed | — | — |
Head-to-head benchmarks (shared only)
| Benchmark | GPT-6.1 Sol | GPT-6.2 Sol |
|---|---|---|
| LiveBench overall | 81.2 | 80.3 |
Cost at three workloads
| Workload | GPT-6.1 Sol | GPT-6.2 Sol |
|---|---|---|
| Light — 1M in / 250K out | $4.50 | $4.50 |
| Standard — 10M in / 2.5M out | $45.00 | $45.00 |
| Long-context — 50M in / 5M out | $150.00 | $150.00 |
The pick
Pick GPT-6.2 Sol if you want the higher overall League Score.
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, GPT-6.1 Sol or GPT-6.2 Sol?
On overall League Score they are effectively tied — GPT-6.1 Sol scores 89 and GPT-6.2 Sol scores 90. The category verdicts on this page are where the real differences live.
Which is cheaper, GPT-6.1 Sol or GPT-6.2 Sol?
They cost the same on our blended measure: $4.00 per 1M tokens each.
Which has the bigger context window, GPT-6.1 Sol or GPT-6.2 Sol?
Neither — both take 1.1M of context.
Are GPT-6.1 Sol and GPT-6.2 Sol open source?
GPT-6.1 Sol is closed weights — API access only; GPT-6.2 Sol is closed weights — API access only.