GPT-5.4 Mini vs Qwen3.8 2.4T A95B
Qwen3.8 2.4T A95B leads GPT-5.4 Mini on the Artificial Analysis Intelligence Index, 39.9 to 24.1, and GPT-5.4 Mini costs 1.3x less per output token ($4.50 vs $6.00 per million). Updated October 22, 2026; 8 benchmarks have a result for both.
GPT-5.4 Mini or Qwen3.8 2.4T A95B: which to pick
Only GPT-5.4 Mini has a coding score, 35.8 on the Vibe Coding Index; Qwen3.8 2.4T A95B has none, so the two cannot be ranked on coding.
Pick Qwen3.8 2.4T A95B for a larger context window (1.05M against 400K tokens) and work measured by AA Coding Index or SciCode, where it leads.
- Shared results
- 8
- GPT-5.4 Mini only
- 82
- Qwen3.8 2.4T A95B only
- 1
- Like-for-like categories
- 5 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Only GPT-5.4 Mini has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Qwen3.8 2.4T A95B
Qwen3.8 2.4T A95B leads, 39.9 against 24.1.
Same board, both measured
Agentic work
AA Agentic Index
Qwen3.8 2.4T A95B
Qwen3.8 2.4T A95B leads, 50.1 against 17.9.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only GPT-5.4 Mini has a GPQA Diamond result, 83.1%.
Directional only
Math
AIME
No call
Only GPT-5.4 Mini has a AIME result, 95.6%.
Directional only
Knowledge
MMLU Pro
No call
Only GPT-5.4 Mini has a MMLU Pro result, 84.5%.
Directional only
Long documents
Listed context window
Qwen3.8 2.4T A95B
Qwen3.8 2.4T A95B takes 1.05M tokens against 400K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-5.4 Mini
GPT-5.4 Mini $0.0030, Qwen3.8 2.4T A95B $0.0050 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5.4 Mini has the number, $0.70.
Directional only
At a glance
- Coding index
- GPT-5.4 Mini 35.8 from 5 benchmarks, Qwen3.8 2.4T A95B not benchmarked.
- Widest category
- Agentic work, 30.0 points apart on average over 2 shared benchmarks.
- Widest single gap
- AA Agentic Index: GPT-5.4 Mini 17.9 against Qwen3.8 2.4T A95B 50.1, 32.2 points apart on a 0 to 100 scale.
- Output price
- GPT-5.4 Mini $4.50 against Qwen3.8 2.4T A95B $6.00 per million output tokens, 1.3x apart.
- Context window
- GPT-5.4 Mini takes 400K tokens, Qwen3.8 2.4T A95B 1.05M.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | GPT-5.4 Mini | Bars | Qwen3.8 2.4T A95B | Ties |
|---|---|---|---|---|
| Coding | 0 | 2 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 2 | ||
| Reasoning | 0 | 2 | ||
| General | 0 | 1 | ||
| All shared boards | 0 | 8 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
| Benchmark | GPT-5.4 Mini | Qwen3.8 2.4T A95B | Leader |
|---|---|---|---|
| LMArena WebDev | 1397 | Not measured | Only GPT-5.4 Mini measured |
| AA Coding Index | 56.1 | 71.9 | Qwen3.8 2.4T A95B |
| LiveCodeBench (Vals AI) | 81.5% | Not measured | Only GPT-5.4 Mini measured |
| SWE-bench Verified (Vals AI) | 73.0% | Not measured | Only GPT-5.4 Mini measured |
| Terminal-Bench 4 (Vals AI) | 2.5% | Not measured | Only GPT-5.4 Mini measured |
| Vibe Code Bench (Vals AI) | 48.0% | Not measured | Only GPT-5.4 Mini measured |
| Code migration (Vals AI) | 12.9% | Not measured | Only GPT-5.4 Mini measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only GPT-5.4 Mini measured |
| Terminal-Bench 2.1 (Vals AI) | 54.7% | Not measured | Only GPT-5.4 Mini measured |
| SciCode | 52.1% | 54.1% | Qwen3.8 2.4T A95B |
| Terminal-Bench Hard (Artificial Analysis run) | 52.3% | Not measured | Only GPT-5.4 Mini measured |
| FrontierCode | 27.0% | Not measured | Only GPT-5.4 Mini measured |
| WeirdML | 60.3% | Not measured | Only GPT-5.4 Mini measured |
| ALE-Bench | 1188.6 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: coding | 1438 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: software and IT | 1436 | Not measured | Only GPT-5.4 Mini measured |
| LMArena WebDev: React | 1386 | Not measured | Only GPT-5.4 Mini measured |
| LMArena WebDev: HTML | 1419 | Not measured | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 25 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-5.4 Mini | Qwen3.8 2.4T A95B | Leader |
|---|---|---|---|
| AA Intelligence Index | 24.1 | 39.9 | Qwen3.8 2.4T A95B |
| Epoch Capabilities Index | 148.7 | Not measured | Only GPT-5.4 Mini measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-5.4 Mini | Qwen3.8 2.4T A95B | Leader |
|---|---|---|---|
| AA Agentic Index | 17.9 | 50.1 | Qwen3.8 2.4T A95B |
| Finance Agent (Vals AI) | 45.4% | Not measured | Only GPT-5.4 Mini measured |
| Tax Agent Bench (Vals AI) | 8.8% | Not measured | Only GPT-5.4 Mini measured |
| Legal Research Bench (Vals AI) | 12.5% | Not measured | Only GPT-5.4 Mini measured |
| Excel Modeling Benchmark (Vals AI) | 45.4% | Not measured | Only GPT-5.4 Mini measured |
| τ²-Bench Telecom | 83.3% | Not measured | Only GPT-5.4 Mini measured |
| DeepResearch Bench | 36.3% | Not measured | Only GPT-5.4 Mini measured |
| MCP Atlas | 56.7% | 84.5% | Qwen3.8 2.4T A95B |
| Neither model has a result on the other 34 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-5.4 Mini | Qwen3.8 2.4T A95B | Leader |
|---|---|---|---|
| GPQA Diamond | 83.1% | Not measured | Only GPT-5.4 Mini measured |
| MMMU Pro (Vals AI) | 79.3% | Not measured | Only GPT-5.4 Mini measured |
| GPQA Diamond (Artificial Analysis run) | 87.5% | 93.5% | Qwen3.8 2.4T A95B |
| Humanity's Last Exam (Artificial Analysis run) | 28.1% | 42.4% | Qwen3.8 2.4T A95B |
| GPQA Diamond (Epoch AI run) | 86.9% | Not measured | Only GPT-5.4 Mini measured |
| ARC-AGI | 63.7% | Not measured | Only GPT-5.4 Mini measured |
| ARC-AGI-2 | 18.9% | Not measured | Only GPT-5.4 Mini measured |
| Chess puzzles | 23.0% | Not measured | Only GPT-5.4 Mini measured |
| Mystery game puzzles | 11.0% | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: hard prompts | 1424 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: expert | 1435 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: hard prompts in English | 1420 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: diagrams | 1266 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: homework | 1285 | Not measured | Only GPT-5.4 Mini measured |
| Kagi LLM Benchmark | 37.9% | Not measured | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 8 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | GPT-5.4 Mini | Qwen3.8 2.4T A95B | Leader |
|---|---|---|---|
| AIME | 95.6% | Not measured | Only GPT-5.4 Mini measured |
| OTIS Mock AIME | 88.9% | Not measured | Only GPT-5.4 Mini measured |
| FrontierMath, tiers 1 to 3 | 51.2% | Not measured | Only GPT-5.4 Mini measured |
| FrontierMath, tier 4 | 9.8% | Not measured | Only GPT-5.4 Mini measured |
| ProofBench | 21.0% | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: math | 1418 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: mathematical work | 1429 | Not measured | Only GPT-5.4 Mini measured |
| MathArena | Not measured | 31.6% | Only Qwen3.8 2.4T A95B measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index10 boards, none shared
| Benchmark | GPT-5.4 Mini | Qwen3.8 2.4T A95B | Leader |
|---|---|---|---|
| MMLU Pro | 84.5% | Not measured | Only GPT-5.4 Mini measured |
| CaseLaw (Vals AI) | 51.7% | Not measured | Only GPT-5.4 Mini measured |
| CorpFin (Vals AI) | 60.9% | Not measured | Only GPT-5.4 Mini measured |
| TaxEval (Vals AI) | 71.2% | Not measured | Only GPT-5.4 Mini measured |
| MortgageTax (Vals AI) | 63.5% | Not measured | Only GPT-5.4 Mini measured |
| SimpleQA Verified | 29.4% | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: science | 1417 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: medicine and healthcare | 1395 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: legal and government | 1414 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: business and finance | 1418 | Not measured | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 10 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.4 Mini | Qwen3.8 2.4T A95B | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-5.4 Mini | Qwen3.8 2.4T A95B | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 50.8% | Not measured | Only GPT-5.4 Mini measured |
| Vals Multimodal Index | 54.2% | Not measured | Only GPT-5.4 Mini measured |
| IFBench | 73.3% | Not measured | Only GPT-5.4 Mini measured |
| Long context reasoning (AA-LCR) | 77.0% | 80.3% | Qwen3.8 2.4T A95B |
| DTBench | 80.0% | Not measured | Only GPT-5.4 Mini measured |
| LMCA | 40.8% | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text | 1412 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: instruction following | 1405 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: creative writing | 1370 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision | 1245 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: English | 1412 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: non-English | 1405 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: Chinese | 1446 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: German | 1408 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: Japanese | 1375 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: Korean | 1370 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: French | 1441 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: Spanish | 1405 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: Russian | 1417 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: Polish | 1415 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: multi-turn | 1429 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: longer queries | 1408 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: writing and language | 1393 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: entertainment and media | 1373 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: English | 1244 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: Chinese | 1286 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: reading text | 1253 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: humor | 1235 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: recognizing things | 1218 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: creative writing | 1222 | Not measured | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 18 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.4 Mini | Qwen3.8 2.4T A95B | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
GPT-5.4 Mini costs less
Repository review
50K input + 3K output tokens
GPT-5.4 Mini costs less
Agent loop
200K input + 10K output tokens
GPT-5.4 Mini costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | OpenAI GPT-5.4 Mini | Qwen3.8 2.4T A95B |
|---|---|---|
| Maker | OpenAI | Qwen |
| Weights | No public weights listed | Open weights |
| Released | March 17, 2026 | August 12, 2026 |
| Context window | 400K | 1.05M |
| Input $/Mtok | $0.75 | $2.00 |
| Output $/Mtok | $4.50 | $6.00 |
| Coding index | 35.8 | Not benchmarked |
| Independent measurements behind it | 5 | 0 |
| Cost per solved task | $0.70 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.4 Mini better than Qwen3.8 2.4T A95B for coding?
Only GPT-5.4 Mini has a coding score, 35.8 on the Vibe Coding Index; Qwen3.8 2.4T A95B has none, so the two cannot be ranked on coding. Pick Qwen3.8 2.4T A95B for a larger context window (1.05M against 400K tokens) and work measured by AA Coding Index or SciCode, where it leads.
Which is cheaper, GPT-5.4 Mini or Qwen3.8 2.4T A95B?
GPT-5.4 Mini costs $0.75 per million input tokens and $4.50 per million output tokens; Qwen3.8 2.4T A95B costs $2.00 and $6.00. Cost per solved task is known for GPT-5.4 Mini only.
Which has the bigger context window, GPT-5.4 Mini or Qwen3.8 2.4T A95B?
Qwen3.8 2.4T A95B, with 1.05M tokens against 400K.
How many benchmarks is the GPT-5.4 Mini vs Qwen3.8 2.4T A95B comparison based on?
8 benchmarks have a result for both models as of October 22, 2026. GPT-5.4 Mini's coding index rests on 5 independent benchmarks and Qwen3.8 2.4T A95B's on 0. Where only one model has a result, the page says so instead of naming a winner.