PERFORMANCELlama 3.3 70B → Scaleway: throughput ↑ 53%6hPERFORMANCEGLM-5.2 → Scaleway: TTFT ↓ 30%6hPERFORMANCEMistral Medium 3.5 → Scaleway: throughput ↑ 22%6hPERFORMANCEQwen3-235B → Scaleway: throughput ↑ 67%6hPERFORMANCEGPT-5.6 Sol → OpenAI: TTFT ↓ 22%6hPERFORMANCEMistral Large 3 → Mistral AI: TTFT ↓ 21%6hPERFORMANCEGPT-5.6 Luna → OpenAI: throughput ↑ 21%6hPERFORMANCEDeepSeek V4 Flash → Scaleway: throughput ↑ 147%6hPERFORMANCEDeepSeek V4 Flash → Scaleway: TTFT ↓ 71%6hPERFORMANCEGPT-OSS 120B → Scaleway: TTFT ↓ 46%6hPERFORMANCEGPT-OSS 120B → Together AI: TTFT ↓ 40%6hPERFORMANCEKimi K3 → Together AI: TTFT ↓ 20%6hPERFORMANCEDeepSeek V4 Flash → Scaleway: throughput ↑ 36%30hPERFORMANCEDeepSeek V4 Flash → Scaleway: TTFT ↓ 19%30hPERFORMANCEQwen3-235B → Scaleway: throughput ↑ 19%2dPERFORMANCEDeepSeek V4 Flash → Scaleway: throughput ↑ 58%2dPERFORMANCEDeepSeek V4 Flash → Scaleway: TTFT ↑ 21%2dPERFORMANCEGPT-5.6 Sol → OpenAI: throughput ↑ 16%2dPERFORMANCEGPT-OSS 120B → Together AI: TTFT ↑ 22%2dPERFORMANCEKimi K3 → Together AI: throughput ↑ 62%2dPERFORMANCEKimi K3 → Together AI: TTFT ↓ 42%2dPERFORMANCEQwen3-235B → Scaleway: throughput ↑ 30%3dPERFORMANCEDeepSeek V4 Flash → Scaleway: TTFT ↓ 56%3dPERFORMANCELlama 3.3 70B → Scaleway: throughput ↑ 34%3dPERFORMANCELlama 3.3 70B → Scaleway: TTFT ↓ 26%3dPERFORMANCEKimi K3 → Together AI: throughput ↑ 128%3dPERFORMANCEGPT-OSS 120B → Together AI: throughput ↑ 29%3dPERFORMANCEGPT-OSS 120B → Together AI: TTFT ↓ 21%3dPERFORMANCEGPT-OSS 20B → Groq: TTFT ↑ 66%3dPERFORMANCEGLM-5.2 → Together AI: throughput ↑ 47%3dPERFORMANCEMistral Medium 3.5 → Scaleway: TTFT ↑ 18%4dPERFORMANCEGLM-5.2 → Scaleway: throughput ↓ 27%4dPERFORMANCEGLM-5.2 → Scaleway: TTFT ↑ 49%4dPERFORMANCEDeepSeek V4 Flash → Scaleway: throughput ↓ 71%4dPERFORMANCEDeepSeek V4 Flash → Scaleway: TTFT ↑ 190%4dPERFORMANCEGPT-5.6 Luna → OpenAI: throughput ↓ 23%4dPERFORMANCELlama 3.3 70B → Scaleway: TTFT ↑ 60%4dPERFORMANCEGLM-5.2 → Together AI: TTFT ↓ 25%4dPERFORMANCEGPT-OSS 120B → Together AI: throughput ↓ 16%4dPERFORMANCEGPT-OSS 120B → Together AI: TTFT ↓ 17%4d
BENCHMARK

Same Model, Different Infrastructure

The identical open-weight model, measured across every provider that serves it.

Key findings
  • GPT-OSS 120B spans 161–291 ms median TTFT across measured providers — a 1.8× spread on identical weights.
  • Measured reliability on the same model ranges 0.0%–100.0%.
  • Output price for the same tokens spans $0.60–$0.75 per million.

One model, many products

GPT-OSS 120B is the widest-covered model in the measured set (4 providers). Whatever explains the differences — hardware, batching policy, routing, quantisation — the buyer experiences them as different products at different prices wearing the same name.

TTFT161 ms291 ms
Throughput129 tok/s1789 tok/s
Output price$0.60/M$0.75/M
Reliability100.0%100.0%
Measured ranges on GPT-OSS 120B: TTFT, reliability, tools, price · ● MEASURED
What this means for engineers
  • Never extrapolate a model's behaviour from one provider's serving of it.
  • Model benchmarks without an infrastructure axis hide the variable that dominates production experience.
Dataset

Figures recompute from the live rolling window on every visit; the snapshot and versions above are the provenance of the regime that produced them. View the current benchmark →

Cite this researchInferenceBench (2026). Same Model, Different Infrastructure. InferenceBench Research.
← All research
Related research
Same Model, Different Infrastructure · InferenceBench