Compare / head-to-head
GPT-6.1 Solvs
Grok 4.6
GPT-6.1 Sol leads 22 of 24 shared benchmarks. Grok 4.6 is 1.5x 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
22 – 2
GPT-6.1 Sol leads
Cheaper per token
Grok 4.6
1.5x cheaper, input + output
Larger context
GPT-6.1 Sol
1.1M tokens
Providers
2 providers
OpenAI · xAI
GPT-6.1 Sol
OpenAI · released 2026-09-29
textvision
Quality
Benchmark matrix
24 shared · 0 only GPT-6.1 Sol · 14 only Grok 4.6| Benchmark | GPT-6.1 Sol | Grok 4.6 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 24 | ||||
| GPQA Diamond | 95.4% ↗epoch run | 94% ↗epoch run | +1.4 pt | GPT-6.1 Sol |
| LMArena Elo | 1483.2 ↗ | 1453.8 ↗ | +29.4 | GPT-6.1 Sol |
| APEX-Agents (Mercor) | 60% ↗ | 65.3% ↗ | -5.3 pt | Grok 4.6 |
| Chess Puzzles (Epoch AI run) | 61% ↗epoch run | 40% ↗epoch run | +21 pt | GPT-6.1 Sol |
| EBR-bench (Epoch AI run) | 54.3% ↗epoch run | 30.5% ↗epoch run | +23.8 pt | GPT-6.1 Sol |
| FrontierMath Tier 4 v2 (Epoch AI run) | 100% ↗epoch run | 31.7% ↗epoch run | +68.3 pt | GPT-6.1 Sol |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 93.7% ↗epoch run | 66% ↗epoch run | +27.7 pt | GPT-6.1 Sol |
| Furniture Assembly (Epoch AI run) | 80% ↗epoch run | 40% ↗epoch run | +40 pt | GPT-6.1 Sol |
| LiveBench Agentic Coding (LiveBench) | 56.8% ↗ | 57% ↗ | -0.2 pt | Grok 4.6 |
| LiveBench Coding (LiveBench) | 80.7% ↗ | 76.8% ↗ | +3.9 pt | GPT-6.1 Sol |
| LiveBench Data Analysis (LiveBench) | 82.7% ↗ | 73.9% ↗ | +8.8 pt | GPT-6.1 Sol |
| LiveBench Instruction Following (LiveBench) | 74.2% ↗ | 71.9% ↗ | +2.3 pt | GPT-6.1 Sol |
| LiveBench Language (LiveBench) | 90.1% ↗ | 83.7% ↗ | +6.4 pt | GPT-6.1 Sol |
| LiveBench Mathematics (LiveBench) | 96.8% ↗ | 92.6% ↗ | +4.2 pt | GPT-6.1 Sol |
| LiveBench Reasoning (LiveBench) | 92.6% ↗ | 90.5% ↗ | +2.1 pt | GPT-6.1 Sol |
| LMArena Agent (LMArena) | 0.1123 ↗ | 0.0128 ↗ | +0.1 | GPT-6.1 Sol |
| LMArena Vision (LMArena) | 1290.6 ↗ | 1263.5 ↗ | +27.1 | GPT-6.1 Sol |
| LMArena WebDev (LMArena) | 1757.8 ↗ | 1619.5 ↗ | +138.3 | GPT-6.1 Sol |
| Mystery Game Puzzles (Epoch AI run) | 80% ↗epoch run | 34% ↗epoch run | +46 pt | GPT-6.1 Sol |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 100% ↗epoch run | 99.2% ↗epoch run | +0.8 pt | GPT-6.1 Sol |
| SAGE (Vals AI) | 46.5% ↗ | 28.9% ↗ | +17.6 pt | GPT-6.1 Sol |
| SimpleBench (SimpleBench) | 82.9% ↗ | 75.9% ↗ | +7 pt | GPT-6.1 Sol |
| SimpleQA Verified | 73.9% ↗epoch run | 49.3% ↗epoch run | +24.6 pt | GPT-6.1 Sol |
| Terminal-Bench 4.0 (Vals AI) | 55.1% ↗ | 17.2% ↗ | +37.9 pt | GPT-6.1 Sol |
| Only GPT-6.1 Sol reports · 0 | ||||
| GPT-6.1 Sol reports nothing Grok 4.6 does not. | ||||
| Only Grok 4.6 reports · 14 | ||||
| AA-Briefcase | not reported | 1577 ↗ | — | — |
| APEX-Agents | not reported | 57.5% ↗ | — | — |
| APEX-SWE | not reported | 56.4% ↗ | — | — |
| Artificial Analysis Intelligence Index | not reported | 61 ↗ | — | — |
| CursorBench 3.2 | not reported | 69.9% ↗ | — | — |
| DeepSWE v1.1 | not reported | 65.9% ↗ | — | — |
| DeepSWE v1.1 (Datacurve) | not reported | 67.5% ↗ | — | — |
| FrontierCode v1.1 (Extended) | not reported | 61.3% ↗ | — | — |
| FrontierSWE V2 (Proximal Labs) | not reported | 25.3% ↗ | — | — |
| GDPVal-AA v2 | not reported | 1753 ↗ | — | — |
| Harvey LAB (Vals) | not reported | 15.8% ↗ | — | — |
| Terminal-Bench 3.0 | not reported | 26% ↗ | — | — |
| Vending-Bench 2 (Andon Labs) | not reported | 9047.03 ↗ | — | — |
| WeirdML (Håvard Tveit Ihle) | not reported | 67.3% ↗ | — | — |
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 GPT-6.1 Sol minus Grok 4.6 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 | GPT-6.1 Sol | Grok 4.6 | Edge |
|---|---|---|---|
| Context window | 1.1M tokens | 500K tokens | GPT-6.1 Sol |
| Max output | 128K tokens | — | — |
| Input price / 1M | $2 ↗ | $2 ↗ | Tie |
| Output price / 1M | $10 ↗ | $6 ↗ | Grok 4.6 |
| Cached input / 1M | $0.1 ↗ | $0.5 ↗ | GPT-6.1 Sol |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $12 | $8 | Grok 4.6 |
| Modalities | text · vision | text · vision | Tie |
| Released | 2026-09-29 | 2026-08-12 | — |
| Cited benchmark scores | 24 | 43 | — |
Reliability
Provider status
Live from /statusMore matchups
GPT-6.1 Sol vs …
Models sharing the most benchmarksMore matchups
Grok 4.6 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run GPT-6.1 Sol and Grok 4.6 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.