Model comparison
GPT-6 Sol vs Grok 4.3
GPT-6 Sol is the stronger model overall, scoring 49.2 to 43.6 on the Noometry Index. Grok 4.3 costs 2.6× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Summary
- They share 16 benchmarks with published results for both. GPT-6 Sol scores higher in 8 categories and Grok 4.3 in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-6 Sol leads 59.6 to 41.3.
- The biggest single-benchmark swing is NYT Connections (extended): 90.1% for GPT-6 Sol and 55.2% for Grok 4.3.
- Grok 4.3 is cheaper at $1.25 / $2.50 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 1M.
Side by side
| GPT-6 Sol | Grok 4.3 | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 49.2 | 43.6 |
| Released | 2026-09-22 | 2026-04-17 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 128K | 30K |
| Input $ / M tokens | $2 | $1.25 |
| Output $ / M tokens | $10 | $2.50 |
| Results tracked | 22 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
GPT-6 Sol: 59.6 (#11), Grok 4.3: 41.3 (#117)
| Benchmark | GPT-6 Sol | Grok 4.3 |
|---|---|---|
| LMArena WebDev | 1692 | 1357 |
| LMArena Coding | 1453 | 1415 |
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| SciCode | — | 47.3% |
| WeirdML | — | 49.9% |
| ALE-Bench | — | 944.17 |
Agentic & Tool Use GPT-6 Sol leads
GPT-6 Sol: 33.5 (#49), Grok 4.3: 27.6 (#93)
| Benchmark | GPT-6 Sol | Grok 4.3 |
|---|---|---|
| GDP.pdf | 28% | 8% |
| LMArena Search | — | 1165 |
| Vending-Bench 2 | — | 35.26 |
Reasoning GPT-6 Sol leads
GPT-6 Sol: 49.3 (#34), Grok 4.3: 34.9 (#60)
| Benchmark | GPT-6 Sol | Grok 4.3 |
|---|---|---|
| NYT Connections (extended) | 90.1% | 55.2% |
| LMArena Hard Prompts | 1420 | 1397 |
| CritPt | — | 8% |
| Chess Puzzles | — | 25% |
| EBR-Bench | 53.3% | — |
| DTBench | — | 90.7% |
| LMCA | — | 38.3% |
| Epoch Capabilities Index | — | 149.13 |
| ForecastBench | — | 60.3 |
Math Grok 4.3 leads
GPT-6 Sol: 35.8 (#135), Grok 4.3: 45.8 (#60)
| Benchmark | GPT-6 Sol | Grok 4.3 |
|---|---|---|
| LMArena Math | 1404 | 1388 |
| FrontierMath (Tiers 1-3) | — | 42.8% |
| FrontierMath Tier 4 | — | 14.6% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| ProofBench | — | 11% |
Knowledge Grok 4.3 leads
GPT-6 Sol: 43.0 (#87), Grok 4.3: 52.5 (#57)
| Benchmark | GPT-6 Sol | Grok 4.3 |
|---|---|---|
| LMArena Expert | 1449 | 1385 |
| GPQA Diamond | — | 88.8% |
| SimpleQA Verified | — | 33.2% |
| Vectara Hallucination Rate | 6.5% | — |
Multimodal GPT-6 Sol leads
GPT-6 Sol: 47.6 (#9), Grok 4.3: 31.6 (#96)
| Benchmark | GPT-6 Sol | Grok 4.3 |
|---|---|---|
| LMArena Vision | — | 1231 |
| Blueprint-Bench 2 | — | 0% |
| Furniture Assembly | 58.3% | — |
Multilingual Too close to call
GPT-6 Sol: 51.0 (#113), Grok 4.3: 50.7 (#114)
| Benchmark | GPT-6 Sol | Grok 4.3 |
|---|---|---|
| LMArena Non-English | 1389 | 1385 |
| LMArena Chinese | 1416 | 1423 |
| LMArena Russian | 1407 | 1399 |
| LMArena Spanish | 1377 | 1402 |
| LMArena French | — | 1412 |
| LMArena German | — | 1395 |
| LMArena Japanese | — | 1379 |
| LMArena Korean | — | 1357 |
Instruction Following GPT-6 Sol leads
GPT-6 Sol: 74.4 (#97), Grok 4.3: 72.3 (#135)
| Benchmark | GPT-6 Sol | Grok 4.3 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1366 |
Long Context Too close to call
GPT-6 Sol: 43.2 (#100), Grok 4.3: 42.5 (#118)
| Benchmark | GPT-6 Sol | Grok 4.3 |
|---|---|---|
| LMArena Longer Query | 1415 | 1393 |
Writing & Preference GPT-6 Sol leads
GPT-6 Sol: 72.3 (#15), Grok 4.3: 58.6 (#112)
| Benchmark | GPT-6 Sol | Grok 4.3 |
|---|---|---|
| LMArena Text | 1396 | 1397 |
| LMArena Creative Writing | 1392 | 1380 |
| LMArena Multi-Turn | 1405 | 1406 |
| EQ-Bench Creative Writing | 2125 | — |
| EQ-Bench 4 | — | 1075 |
Frequently asked questions
Is GPT-6 Sol better than Grok 4.3?
GPT-6 Sol is the stronger model overall, scoring 49.2 to 43.6 on the Noometry Index. Grok 4.3 costs 2.6× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Which is cheaper, GPT-6 Sol or Grok 4.3?
Grok 4.3 is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is GPT-6 Sol or Grok 4.3 better for coding?
GPT-6 Sol scores higher on coding benchmarks: 59.6 versus 41.3 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 1M.
How many benchmarks do GPT-6 Sol and Grok 4.3 share?
16 benchmarks have published results for both models. GPT-6 Sol has 22 scored results on Noometry and Grok 4.3 has 40.