Compare / head-to-head
Gemini 3.8 Flashvs
GPT-6.1 Sol
GPT-6.1 Sol leads 19 of 23 shared benchmarks. Gemini 3.8 Flash is 2.7x cheaper per token. GPT-6.1 Sol has the larger context window (1.1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
3 – 19
GPT-6.1 Sol leads · 1 tied
Cheaper per token
Gemini 3.8 Flash
2.7x cheaper, input + output
Larger context
GPT-6.1 Sol
1.1M tokens
Providers
2 providers
Google · OpenAI
Gemini 3.8 Flash
Google · released 2026-09-02
textvisionaudio
GPT-6.1 Sol
OpenAI · released 2026-09-29
textvision
Quality
Benchmark matrix
23 shared · 14 only Gemini 3.8 Flash · 1 only GPT-6.1 Sol| Benchmark | Gemini 3.8 Flash | GPT-6.1 Sol | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 23 | ||||
| GPQA Diamond | 95.3% ↗ | 95.4% ↗epoch run | -0.1 pt | GPT-6.1 Sol |
| LMArena Elo | 1494.8 ↗ | 1483.2 ↗ | +11.6 | Gemini 3.8 Flash |
| APEX-Agents (Mercor) | 64.3% ↗ | 60% ↗ | +4.3 pt | Gemini 3.8 Flash |
| Chess Puzzles (Epoch AI run) | 61% ↗epoch run | 61% ↗epoch run | 0 | Tie |
| FrontierMath Tier 4 v2 (Epoch AI run) | 22% ↗epoch run | 100% ↗epoch run | -78 pt | GPT-6.1 Sol |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 68.4% ↗epoch run | 93.7% ↗epoch run | -25.3 pt | GPT-6.1 Sol |
| Furniture Assembly (Epoch AI run) | 31.7% ↗epoch run | 80% ↗epoch run | -48.3 pt | GPT-6.1 Sol |
| LiveBench Agentic Coding (LiveBench) | 54.2% ↗ | 56.8% ↗ | -2.6 pt | GPT-6.1 Sol |
| LiveBench Coding (LiveBench) | 72.5% ↗ | 80.7% ↗ | -8.2 pt | GPT-6.1 Sol |
| LiveBench Data Analysis (LiveBench) | 54% ↗ | 82.7% ↗ | -28.7 pt | GPT-6.1 Sol |
| LiveBench Instruction Following (LiveBench) | 81.4% ↗ | 74.2% ↗ | +7.2 pt | Gemini 3.8 Flash |
| LiveBench Language (LiveBench) | 87.8% ↗ | 90.1% ↗ | -2.3 pt | GPT-6.1 Sol |
| LiveBench Mathematics (LiveBench) | 91.6% ↗ | 96.8% ↗ | -5.2 pt | GPT-6.1 Sol |
| LiveBench Reasoning (LiveBench) | 89.3% ↗ | 92.6% ↗ | -3.3 pt | GPT-6.1 Sol |
| LMArena Agent (LMArena) | 0.0297 ↗ | 0.1123 ↗ | -0.1 | GPT-6.1 Sol |
| LMArena Vision (LMArena) | 1290.3 ↗ | 1290.6 ↗ | -0.3 | GPT-6.1 Sol |
| LMArena WebDev (LMArena) | 1582.7 ↗ | 1757.8 ↗ | -175.1 | GPT-6.1 Sol |
| Mystery Game Puzzles (Epoch AI run) | 47% ↗epoch run | 80% ↗epoch run | -33 pt | GPT-6.1 Sol |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 98.9% ↗epoch run | 100% ↗epoch run | -1.1 pt | GPT-6.1 Sol |
| SAGE (Vals AI) | 35.1% ↗ | 46.5% ↗ | -11.4 pt | GPT-6.1 Sol |
| SimpleBench (SimpleBench) | 82.4% ↗ | 82.9% ↗ | -0.5 pt | GPT-6.1 Sol |
| SimpleQA Verified | 69.7% ↗epoch run | 73.9% ↗epoch run | -4.2 pt | GPT-6.1 Sol |
| Terminal-Bench 4.0 (Vals AI) | 19.2% ↗ | 55.1% ↗ | -35.9 pt | GPT-6.1 Sol |
| Only Gemini 3.8 Flash reports · 14 | ||||
| CharXiv Reasoning (no tools) | 86.2% ↗ | not reported | — | — |
| DeepSWE v1.1 | 73.7% ↗ | not reported | — | — |
| DeepSWE v1.1 (Datacurve) | 73.8% ↗ | not reported | — | — |
| FrontierSWE V2 (Proximal Labs) | 19.6% ↗ | not reported | — | — |
| GDPVal-AA v2 | 1545 ↗ | not reported | — | — |
| Harvey's Legal Agent Benchmark | 10% ↗ | not reported | — | — |
| HLE-Verified | 54.9% ↗ | not reported | — | — |
| LABBench2 | 86.2% ↗ | not reported | — | — |
| OSWorld-2.0 | 59% ↗ | not reported | — | — |
| Terminal-bench 2.1 | 89.4% ↗ | not reported | — | — |
| Terminal-bench 4.0 | 19.1% ↗ | not reported | — | — |
| Vals Finance Agent v2 | 61.4% ↗ | not reported | — | — |
| Vending-Bench 2 (Andon Labs) | 5093.79 ↗ | not reported | — | — |
| WeirdML (Håvard Tveit Ihle) | 84.8% ↗ | not reported | — | — |
| Only GPT-6.1 Sol reports · 1 | ||||
| EBR-bench (Epoch AI run) | not reported | 54.3% ↗epoch run | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Gemini 3.8 Flash minus GPT-6.1 Sol in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Gemini 3.8 Flash | GPT-6.1 Sol | Edge |
|---|---|---|---|
| Context window | 1.0M tokens | 1.1M tokens | GPT-6.1 Sol |
| Max output | 66K tokens | 128K tokens | GPT-6.1 Sol |
| Input price / 1M | $0.75 ↗ | $2 ↗ | Gemini 3.8 Flash |
| Output price / 1M | $3.75 ↗ | $10 ↗ | Gemini 3.8 Flash |
| Cached input / 1M | $0.075 ↗ | $0.1 ↗ | Gemini 3.8 Flash |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $4.5 | $12 | Gemini 3.8 Flash |
| Modalities | text · vision · audio | text · vision | Gemini 3.8 Flash |
| Released | 2026-09-02 | 2026-09-29 | — |
| Cited benchmark scores | 43 | 24 | — |
Reliability
Provider status
Live from /statusMore matchups
Gemini 3.8 Flash vs …
Models sharing the most benchmarksMore matchups
GPT-6.1 Sol vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Gemini 3.8 Flash and GPT-6.1 Sol on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.