Compare / head-to-head
GPT-5.4vsQwen3-Max
GPT-5.4 leads 3 of 4 shared benchmarks. Qwen3-Max is 2.4x cheaper per token. GPT-5.4 has the larger context window (1.1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
3 – 1
GPT-5.4 leads
Cheaper per token
Qwen3-Max
2.4x cheaper, input + output
Larger context
GPT-5.4
1.1M tokens
Provider uptime (30d)
94.3662% · —
OpenAI · Qwen
GPT-5.4
OpenAI · released 2026-03-05
textvision
Quality
Benchmark matrix
4 shared · 16 only GPT-5.4 · 1 only Qwen3-Max| Benchmark | GPT-5.4 | Qwen3-Max | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 4 | ||||
| GPQA Diamond | 92.8% ↗ | 72.6% ↗epoch | +20.2 pt | GPT-5.4 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 78.6% ↗epoch | 18.9% ↗epoch | +59.7 pt | GPT-5.4 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 97.8% ↗epoch | 73.3% ↗epoch | +24.5 pt | GPT-5.4 |
| SimpleQA Verified | 45.1% ↗epoch | 48.7% ↗epoch | -3.6 pt | Qwen3-Max |
| Only GPT-5.4 reports · 16 | ||||
| AIME 2026 | 99.2% ↗matharena ⚠ | not reported | — | — |
| Humanity's Last Exam (no tools) | 39.8% ↗ | not reported | — | — |
| LMArena Elo | 1452.6 ↗ | not reported | — | — |
| BrowseComp | 82.7% ↗ | not reported | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | 49% ↗epoch | not reported | — | — |
| GDPval (wins or ties) | 83% ↗ | not reported | — | — |
| Humanity's Last Exam (with tools) | 52.1% ↗ | not reported | — | — |
| MCP Atlas | 67.2% ↗ | not reported | — | — |
| MMMU-Pro (no tools) | 81.2% ↗ | not reported | — | — |
| MMMU-Pro (with tools) | 82.1% ↗ | not reported | — | — |
| OSWorld-Verified | 75% ↗ | not reported | — | — |
| SWE-Bench Pro | 57.7% ↗ | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 76.9% ↗epoch | not reported | — | — |
| Tau2-bench Telecom | 98.9% ↗ | not reported | — | — |
| Terminal-Bench 2.0 | 75.1% ↗ | not reported | — | — |
| Toolathlon | 54.6% ↗ | not reported | — | — |
| Only Qwen3-Max reports · 1 | ||||
| SWE-bench Verified | not reported | 69.6% ↗ | — | — |
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-5.4 minus Qwen3-Max 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-5.4 | Qwen3-Max | Edge |
|---|---|---|---|
| Context window | 1.1M tokens | 262K tokens | GPT-5.4 |
| Max output | 128K tokens | — | — |
| Input price / 1M | $2.5 ↗ | $1.2 ↗ | Qwen3-Max |
| Output price / 1M | $15 ↗ | $6 ↗ | Qwen3-Max |
| Cached input / 1M | $0.25 ↗ | $0.12 ↗ | Qwen3-Max |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $17.5 | $7.2 | Qwen3-Max |
| Modalities | text · vision | text | GPT-5.4 |
| Released | 2026-03-05 | 2025-09-23 | — |
| Cited benchmark scores | 21 | 5 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
GPT-5.4 vs …
Models sharing the most benchmarksMore matchups
Qwen3-Max vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run GPT-5.4 and Qwen3-Max on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.