Grok 4.7 vs Nemotron 3.5 Super VL 120B A12B vs Qwen3.8 Max 0902
No independent capability benchmark covers every model here yet. The score uses price and context window.No independent capability benchmark covers every model here yet. The score uses context window.
xAI
Grok 4.7
34/100- ECI156.4
- Price$2.00 / $6.00
- Context500K
NVIDIA
Nemotron 3.5 Super VL 120B A12B
71/100- ECI—
- Price$0.20 / $0.50
- Context1.05M
Alibaba (Qwen)
Qwen3.8 Max 0902
37/100- ECI156.0
- Price$2.00 / $6.00
- Context1M
xAI
Grok 4.7
53/100- ECI156.4
- Price$2.00 / $6.00
- Context500K
NVIDIA
Nemotron 3.5 Super VL 120B A12B
65/100- ECI—
- Price$0.20 / $0.50
- Context1.05M
Alibaba (Qwen)
Qwen3.8 Max 0902
64/100- ECI156.0
- Price$2.00 / $6.00
- Context1M
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (Nemotron 3.5 Super VL 120B A12B 71/100, Qwen3.8 Max 0902 37/100, Grok 4.7 34/100) compare the available specifications and price. The score weighs price 71%, context window 29%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.There is not enough shared capability evidence to name an overall winner. The scores (Nemotron 3.5 Super VL 120B A12B 65/100, Qwen3.8 Max 0902 64/100, Grok 4.7 53/100) compare the available specifications only. The score weighs context window 100%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceNemotron 3.5 Super VL 120B A12BNemotron 3.5 Super VL 120B A12B $0.275 · Grok 4.7 $3.00 · Qwen3.8 Max 0902 $3.00 per 1M tokens (3:1 blend)
- Longest contextNemotron 3.5 Super VL 120B A12BNemotron 3.5 Super VL 120B A12B 1,048,576 · Qwen3.8 Max 0902 1,000,000 · Grok 4.7 500,000 tokens
- Widest inputsQwen3.8 Max 0902Grok 4.7: Text, Images, PDFs · Nemotron 3.5 Super VL 120B A12B: Text, Images, Video · Qwen3.8 Max 0902: Text, Images, PDFs, Video
- Self-hostingNemotron 3.5 Super VL 120B A12BPublishes downloadable weights
| Measure | Weight | Grok 4.7 | Nemotron 3.5 Super VL 120B A12B | Qwen3.8 Max 0902 |
|---|---|---|---|---|
| Price | 71% | 26 | 73 | 26 |
| Context window | 29% | 53 | 65 | 64 |
| Specs & price only | 100% | 34/100 | 71/100 | 37/100 |
Left out because at least one model lacks the data: capability and inputs & features. The remaining weights were rescaled.
| Measure | Weight | Grok 4.7 | Nemotron 3.5 Super VL 120B A12B | Qwen3.8 Max 0902 |
|---|---|---|---|---|
| Context window | 100% | 53 | 65 | 64 |
| Specs only | 100% | 53/100 | 65/100 | 64/100 |
Left out because at least one model lacks the data: capability and inputs & features. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Unavailable specifications are marked “Not published”. Publisher results include their evaluation settings and source.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 156.4 (best) | Not published | 156.0 |
| ECI rank | #39 of 159 (best) | Not published | #42 of 159 |
| ECI confidence interval | 154.5–158.5 | Not published | 153.9–158.3 |
| ECI evaluation date | Sep 21, 2026 | Not published | Sep 1, 2026 |
| Documented capabilities | xAI's frontier model for long-running agents, coding, knowledge work, and visual projects | NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use | 2026-09-02 upgraded snapshot of Qwen3.8 Max with stronger coding, collaborative agents, and multimodal document understanding |
| Model parameters | Not published | Not published | Not published |
| Output modalities | Text | Text | Text |
| GPQA DiamondGraduate-level science questions | 92.7%xhigh (best) | Not published | 92.3%xhigh |
| FrontierMath Tiers 1–3Research-level mathematics | 53.0%xhigh | Not published | 65.6%xhigh (best) |
| OTIS Mock AIME 2024–2025Competition mathematics | 98.1%xhigh | Not published | 100%xhigh (best) |
| SimpleQA VerifiedShort factual questions | 56.0%xhigh (best) | Not published | 47.3%xhigh |
| Publisher-reported benchmarks | |||
| CursorBench 4.0xhigh effort | 46.3scoreReported resultSep 21, 2026 | Not published | Not published |
| DeepSWE 1.1high effort | 71scoreReported resultSep 21, 2026 | Not published | Not published |
| EEBenchxhigh effort | 64scoreReported resultSep 21, 2026 | Not published | Not published |
| AA-Briefcase 1.1xhigh effort | 1657EloReported resultSep 21, 2026 | Not published | Not published |
| Terminal-Bench 4.0xhigh effort | 37.6scoreReported resultSep 21, 2026 | Not published | Not published |
| Harvey Legal Agent Benchmarkxhigh effort | 19.6scoreReported resultSep 21, 2026 | Not published | Not published |
| HealthBenchxhigh effort; professional | 56.7scoreReported resultSep 21, 2026 | Not published | Not published |
| GDPvalxhigh effort | 1695EloReported resultSep 21, 2026 | Not published | Not published |
| Price per million tokens | |||
| Input | $2.00 | $0.20 (best) | $2.00 |
| Output | $6.00 | $0.50 (best) | $6.00 |
| Cached input | $0.50 | Not published | Not published |
| Blended (3:1) | $3.00 | $0.275 (best) | $3.00 |
| Long-context rate | Over 200K: $4.00 / $12.00 | Same rate | Same rate |
| Price source | Official xAI API | Median of 15 providers | Median of 9 providers |
| Limits | |||
| Context window | 500,000 tokens | 1,048,576 tokens (best) | 1,000,000 tokens |
| Max input | Not published | Not published | Not published |
| Max output | 500,000 tokens (best) | 8,192 tokens | 131,072 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | Yes | No | Yes |
| Audio | No | No | No |
| Video | No | Yes | Yes |
| Reasoning | Yeslow · medium · high · xhigh | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Not published | Not published |
| File attachments | Yes | Yes | Yes |
| Temperature control | Yes | Yes | Yes |
| Reasoning control | effort | toggle | always |
| Availability | |||
| Weights | Proprietary | Open | Proprietary |
| API model ID | grok-4.7 | nvidia/nemotron-3.5-super-vl-120b-a12b | Not published |
| API providers | 35 (best) | 19 | 9 |
| Released | Sep 21, 2026 | Oct 15, 2026 | Sep 2, 2026 |
| Knowledge cutoff | May 2026 | Not published | Not published |
| Publisher documentation | Publisher documentation | Publisher documentation · Model weights | Not published |
| Source metadata updated | Sep 21, 2026 | Oct 15, 2026 | Sep 2, 2026 |
| Data sources | models.dev · Epoch AI | models.dev · Epoch AI | models.dev · Epoch AI |
| Catalog checked | Nov 22, 2026 | Nov 22, 2026 | Nov 22, 2026 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Grok 4.7$32.00
Nemotron 3.5 Super VL 120B A12B$3.00
Qwen3.8 Max 0902$32.00
Which should you choose?
Which is better: Grok 4.7, Nemotron 3.5 Super VL 120B A12B or Qwen3.8 Max 0902?
There is not enough shared capability evidence to name an overall winner. The scores (Nemotron 3.5 Super VL 120B A12B 71/100, Qwen3.8 Max 0902 37/100, Grok 4.7 34/100) compare the available specifications and price. The score weighs price 71%, context window 29%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.There is not enough shared capability evidence to name an overall winner. The scores (Nemotron 3.5 Super VL 120B A12B 65/100, Qwen3.8 Max 0902 64/100, Grok 4.7 53/100) compare the available specifications only. The score weighs context window 100%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Grok 4.7, Nemotron 3.5 Super VL 120B A12B or Qwen3.8 Max 0902?
Nemotron 3.5 Super VL 120B A12B is cheaper at $0.20 input / $0.50 output per million tokens (median across 15 API providers; free on Nvidia). Grok 4.7 costs $2.00 input / $6.00 output per million tokens (official xAI API price); Qwen3.8 Max 0902 costs $2.00 input / $6.00 output per million tokens (median across 9 API providers). At a typical mix of three input tokens to one output token, that is $0.275 per million tokens for Nemotron 3.5 Super VL 120B A12B versus $3.00 for Grok 4.7 (11× as much) and $3.00 for Qwen3.8 Max 0902 (11× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Grok 4.7 has an ECI of 156.4, Nemotron 3.5 Super VL 120B A12B has not been scored yet and Qwen3.8 Max 0902 has an ECI of 156.0.
Which is better for coding?
There are no published SWE-bench Verified results for Grok 4.7, Nemotron 3.5 Super VL 120B A12B and Qwen3.8 Max 0902 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Nemotron 3.5 Super VL 120B A12B has the largest context window at 1,048,576 tokens, against 1,000,000 for Qwen3.8 Max 0902 and 500,000 for Grok 4.7. Maximum output per response: Grok 4.7 up to 500,000, Nemotron 3.5 Super VL 120B A12B up to 8,192, Qwen3.8 Max 0902 up to 131,072 tokens.
Which can read images, PDFs, audio or video?
Grok 4.7 accepts text, images and PDFs; Nemotron 3.5 Super VL 120B A12B accepts text, images and video; Qwen3.8 Max 0902 accepts text, images, PDFs and video. Qwen3.8 Max 0902 handles the widest range of inputs.
Are any of these open source?
Nemotron 3.5 Super VL 120B A12B publishes its weights and can be self-hosted; Grok 4.7 and Qwen3.8 Max 0902 is proprietary.
Which is newer?
Nemotron 3.5 Super VL 120B A12B is the newest, released Oct 15, 2026. Grok 4.7 came out Sep 21, 2026; Qwen3.8 Max 0902 came out Sep 2, 2026. Knowledge cutoff: Grok 4.7 May 2026.
How do you decide the winner?
This rating uses price (71%, blended price per million tokens (3 input : 1 output), log scale); context window (29%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 22, 2026.This rating uses context window (100%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 22, 2026.