// head_to_head
GPT-6 Sol vs SpaceXAI: Grok 4.7
Published LiveBench scores across all seven categories, live list pricing, context windows, and the measured cost of a point of capability — for both models, side by side.
GPT-6 Sol scores higher, SpaceXAI: Grok 4.7 costs less — it depends on your workload.
GPT-6 Sol is ahead by 1.8 points overall, and SpaceXAI: Grok 4.7 lists 1.7× cheaper per blended million tokens. Whether 1.8 points is worth that depends on how much a wrong answer costs you. The two cost measures disagree here, which is worth knowing: SpaceXAI: Grok 4.7 has the lower sticker price, but GPT-6 Sol earns each point of capability for less — $0.1444 against $0.4062 — because per-token rates do not predict how many tokens a model actually spends on a task.
openai
GPT-6 Sol
- Blended / 1M
- $4.00
- Context
- 1.1M
- Released
- Sep 22, 2026
- Overall score
- 79.2
x-ai
SpaceXAI: Grok 4.7
- Blended / 1M
- $2.40
- Context
- 500K
- Released
- Sep 21, 2026
- Overall score
- 77.4
Specs and pricing
| Metric | GPT-6 Sol | SpaceXAI: Grok 4.7 |
|---|---|---|
| LiveBench overall Mean of the seven LiveBench category scores, 0–100. Higher is better. | 79.2win | 77.4 |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | $0.1444win | $0.4062 |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $4.00 | $2.40win |
| Input price / 1M | $2.00 | $1.60win |
| Output price / 1M | $10.00 | $4.80win |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | $0.200win | $0.400 |
| Context window | 1.1Mwin | 500K |
| Max output tokens | 128K | 450Kwin |
Benchmarks by category
An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — GPT-6 Sol on top, SpaceXAI: Grok 4.7 below, both out of 100.
What each one costs to run
Per-token prices are hard to feel. These are monthly list costs for both models across five workload shapes, using each provider's published cached-input rate where there is one.
| Workload | GPT-6 Sol | SpaceXAI: Grok 4.7 |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $1,150/mo | $681.60/mo |
| RAG assistant 8K in / 600 out × 100K requests | $1,480/mo | $1,088/mo |
| Coding agent 40K in / 4K out × 20K requests | $1,392/mo | $992.00/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $2,660/mo | $1,900/mo |
| Bulk classification 500 in / 20 out × 5M requests | $5,100/mo | $3,880/mo |
Which should you pick?
You are running this at volume
GPT-6 Sol
Lowest measured cost per point of capability at $0.1444 per point — the gap compounds with every request.
Quality matters more than the bill
GPT-6 Sol
Highest overall LiveBench score of the two at 79.2.
The workload is coding or agentic work
SpaceXAI: Grok 4.7
Leads on agentic coding — 54.0 against 52.9.
You need to fit large documents in one call
GPT-6 Sol
Wider context window — 1.1M against 500K.
GPT-6 Sol vs SpaceXAI: Grok 4.7 FAQ
Which is better, GPT-6 Sol or SpaceXAI: Grok 4.7?
GPT-6 Sol scores higher, SpaceXAI: Grok 4.7 costs less — it depends on your workload. GPT-6 Sol is ahead by 1.8 points overall, and SpaceXAI: Grok 4.7 lists 1.7× cheaper per blended million tokens. Whether 1.8 points is worth that depends on how much a wrong answer costs you. The two cost measures disagree here, which is worth knowing: SpaceXAI: Grok 4.7 has the lower sticker price, but GPT-6 Sol earns each point of capability for less — $0.1444 against $0.4062 — because per-token rates do not predict how many tokens a model actually spends on a task.
Is GPT-6 Sol cheaper than SpaceXAI: Grok 4.7?
SpaceXAI: Grok 4.7 is cheaper. On a 3:1 input:output blend, GPT-6 Sol lists at $4.00 per million tokens and SpaceXAI: Grok 4.7 at $2.40 — SpaceXAI: Grok 4.7 is 1.7× cheaper. Input and output are priced separately — GPT-6 Sol charges $2.00 in and $10.00 out, SpaceXAI: Grok 4.7 charges $1.60 and $4.80 — so the model that looks cheaper flips depending on how output-heavy your workload is.
GPT-6 Sol vs SpaceXAI: Grok 4.7: which scores higher on benchmarks?
GPT-6 Sol scores 79.2 and SpaceXAI: Grok 4.7 scores 77.4 overall on LiveBench, the mean of its seven categories. That is a 1.8-point lead for GPT-6 Sol. Category scores differ from the overall figure — a model can lead on reasoning and trail on coding, which the per-category table above breaks out.
Which gives better value for money, GPT-6 Sol or SpaceXAI: Grok 4.7?
GPT-6 Sol. Cost per point divides the measured dollars LiveBench spent running the benchmark by the score it earned, so it captures something token pricing misses: a reasoning model can emit many times more tokens than its per-token rate suggests. GPT-6 Sol works out at $0.1444 per point and SpaceXAI: Grok 4.7 at $0.4062.
Does GPT-6 Sol or SpaceXAI: Grok 4.7 have a bigger context window?
GPT-6 Sol has the larger context window: 1.1M for GPT-6 Sol against 500K for SpaceXAI: Grok 4.7. Note that a window you can fill is not a window you should fill — retrieval quality usually degrades well before the limit, and you pay for every token you put in it.
Do GPT-6 Sol and SpaceXAI: Grok 4.7 support prompt caching?
Both publish a cached-input rate: $0.200 per million for GPT-6 Sol and $0.400 for SpaceXAI: Grok 4.7, against full input rates of $2.00 and $1.60. On a workload with a long stable prefix — a system prompt, a tool schema, a retrieved corpus — that changes the economics more than the headline price does.
Related comparisons
How these numbers are produced
- Price — provider list price from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores — LiveBench release 2026-06-25, using their own category map. Each model shows its strongest published run. A blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
- “Win” — awarded only past a threshold: one full point on a benchmark score, 10% on a price, 25% on a context window. Anything tighter reports as a tie, because effort settings alone move a LiveBench score by more than that.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.