Across 4 comparable benchmarks, Gemini 4 Hydrogen has better reported results on 4 and worse on 0.
Moderate evidence4 of 4 shared results countedHow we compare
Price basis: Standard rates vs listed rates. The price section below shows the applicable periods.
| Fact | Gemini 4 Hydrogen | Qwen4-Max |
|---|---|---|
| Context window | 1M tokens | 1M tokens |
| Input / 1M | $1.50 | $1.50 |
| Output / 1M | $7.50 | $4.50 |
| Blended (4:1) | $1.67 | $1.07 |
| Status | Available | Available |
| Released | November 12, 2026 | November 16, 2026 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 1 shared benchmark grouped by capability on a 0–100 scale. How averages are built
Gemini 4 Hydrogen ahead on 1 of 1 counted
Gemini 4 Hydrogen ahead on 1 of 1 counted
No fixed-scale average — see the rows in Benchmark results
No shared comparable results for Coding, Abstract reasoning, Mathematics, Science & health, Research & search, Long context, Professional work & productivity, Cybersecurity.
Published scores, with matching modes where available. Gaps show Gemini 4 Hydrogen relative to Qwen4-Max. Reading the results
| Benchmark | Gemini 4 Hydrogen | Qwen4-Max | Gap |
|---|---|---|---|
| AutomationBench-AATool Orchestration · Guardrail-safe objective completion rate | 76.1Extra-High · tools | 72.5≠Max · tools | +3.6 pts#6 vs #9 of 18 |
| ChartographyDocuments & Charts · Score | 66.6Extra-High · no tools | 54.2≠Max · tools | 1.23×#20 vs #23 of 29 |
| Agent ArenaPreference Arenas · Net improvement index (percentage points vs. average model) | 14.8Thinking High · tools + web | 7.5≠Max · tools + web | 1.97×#5 vs #12 of 35 |
| Agent Arena IndexPreference Arenas · Agent Arena Index rating (index points) | 1271Thinking High · tools + web | 1189≠Extra-High · tools + internet | 1.07×#9 vs #15 of 36 |
Tool Orchestration · Guardrail-safe objective completion rate
Documents & Charts · Score
Preference Arenas · Net improvement index (percentage points vs. average model)
Preference Arenas · Agent Arena Index rating (index points)
A dash means no result is available.
| Benchmark | Gemini 4 Hydrogen | Qwen4-Max |
|---|---|---|
| HLE | — | 51.7 |
| Terminal-Bench-Science 0.1 | 51.4 | — |
| DeepSWE | — | 75.7 |
| FrontierCS 2 | 44.6 | — |
| ProgramBench | — | 31.5 |
| SWE-sweep | 13.5 | — |
| Terminal-Bench 4.0 | — | 48.5 |
| Terminal-Bench 4.1 | 56.4 | — |
| Vibe Code Bench v1.1 | — | 86.7 |
| Agents' Last Exam v1.1 | — | 46.7 |
| APEX-Agents | — | 72.1 |
| OSWorld 2.1 | 77.6 | — |
| AA Intelligence Index v5.0.1 | — | 42.9 |
| Code Arena WebDev | — | 1750 |
| Vals Index v2.2 | — | 63.2 |
| AA-Briefcase | — | 1686 |
| AutomationBench | 51.1 | — |
| JobBench | — | 68.5 |
| Legal Research Bench | — | 41.4 |
| Tax Agent Bench | — | 40.4 |
| SimpleBench | 91.7 | — |
| Vending-Bench 2 | 14550 | — |
| BioMysteryBench | — | 85.0 |
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
Gemini 4 Hydrogen costs56%morethan Qwen4-Max per million tokens.Using standard rates vs listed rates at this token mix.
Gemini 4 Hydrogen: Standard pricing. Unified context pricing; thinking tokens included in output.
Qwen4-Max: International pricing. context_length <= 1000000 QwenCloud International (Singapore)
| Price / 1M tokens | Gemini 4 Hydrogen | Qwen4-Max | Ratio |
|---|---|---|---|
| Input | $1.50 | $1.50 | 1.00× |
| Output | $7.50 | $4.50 | 1.67× |
| Cached input | $0.075 | $0.075 | 1.00× |
| Cache write | — | $1.88 | — |
| Blended | $1.67 | $1.07 | 1.56× |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
Gemini 4 Hydrogen relative to Qwen4-Max
No matching recorded settings for a cost summary.
Summary: 0 of 1 shared benchmarks have matching recorded settings and sources. The average is a geometric mean of 0 positive-cost ratios, one equal weight per benchmark. This benchmark set can include related tests and indexes; it is not a workload cost estimate.
Settings or sources differ
Settings or sources differ
Settings or sources differ or are not recorded; interpret the comparison with care.
Gemini 4 Hydrogen
Qwen4-Max
| Benchmark | Gemini 4 Hydrogen | Qwen4-Max |
|---|---|---|
| AA Intelligence Index v5.0.1 | Not reported | |
| Agent Arena | $1.5351 / task Median · Net improvement index (percentage points vs. average model): 14.8 Thinking High (With Tools + Internet) | Not reported |
| AutomationBench | $0.82 / task Average · Pass Rate: 51.1 Thinking High (With Tools) · zapier-private-heldout $0.18 / task Average · Pass Rate: 30.6 Thinking Low (With Tools) · zapier-private-heldout $0.41 / task Average · Pass Rate: 46.7 Thinking Medium (With Tools) · zapier-private-heldout | Not reported |
| FrontierCS 2 | Not reported | |
| Legal Research Bench | Not reported | |
| Tax Agent Bench | Not reported | |
| Terminal-Bench 4.0 | Not reported | $3.90 / task Average · Resolution rate (%): 48.5 Unspecified Reasoning (With Tools) · vals-mini-swe |
| Terminal-Bench 4.1 | Not reported | |
| Vals Index v2.2 | Not reported | |
| Vibe Code Bench v1.1 | Not reported |
| Attribute | Gemini 4 Hydrogen | Qwen4-Max |
|---|---|---|
| Availability | Available | Available |
| Provider | Google Deep Mind | Alibaba |
| Model type | Multimodal model | Reasoning model |
| First release | November 12, 2026 | November 16, 2026 |
| Context window | 1M tokens | 1M tokens |
| Max output | 1M tokens | 384K tokens |
| Total parameters | — | 2.4T |
| Active parameters | — | 71B |
| Architecture | Undisclosed | Mixture of Experts (MoE) |
| Documented capabilities | Reasoning, Coding, Tool use, Computer use, Long context, Function calling, Structured output, Web search | Reasoning, Multilingual, Coding, Function calling, Tool use, Structured output, Web search, Long context |
| Knowledge cutoff | 2026-03 | — |
| Input modalities | Text, Image, Audio, Video | Text, Image, Video |
| Output modalities | Text | Text |
| Weights | Closed / API only | Closed / API only |
| Commercial use | Proprietary | Proprietary |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used Gemini 4 Hydrogen or Qwen4-Max? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.