GPT-5.4 vs MiniMax M3.1 Flash
GPT-5.4 leads MiniMax M3.1 Flash on coding, 64.4 to 59.0 on the Vibe Coding Index, and MiniMax M3.1 Flash costs 25.0x less per output token ($0.60 vs $15.00 per million). Updated October 22, 2026; 7 benchmarks have a result for both.
GPT-5.4 or MiniMax M3.1 Flash: which to pick
Pick GPT-5.4 for coding: it scores 64.4 on the Vibe Coding Index against 59.0 for MiniMax M3.1 Flash, though on 3 benchmarks against 4.
Pick MiniMax M3.1 Flash for output tokens 25.0x cheaper ($0.60 vs $15.00 per million) and work measured by LMArena WebDev or Vibe Code Bench (Vals AI), where it leads.
- Shared results
- 7
- GPT-5.4 only
- 111
- MiniMax M3.1 Flash only
- 13
- Like-for-like categories
- 4 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
GPT-5.4
GPT-5.4 scores 64.4 against 59.0.
3 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
MiniMax M3.1 Flash
MiniMax M3.1 Flash leads, 42.7 against 39.0.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only GPT-5.4 has a GPQA Diamond result, 91.7%.
Directional only
Math
AIME
No call
Only GPT-5.4 has a AIME result, 96.7%.
Directional only
Knowledge
MMLU Pro
No call
Only GPT-5.4 has a MMLU Pro result, 87.5%.
Directional only
Web design
Design Arena: websites
No call
Only GPT-5.4 has a Design Arena: websites result, 1198.
Directional only
General
Vals Index
No call
Only MiniMax M3.1 Flash has a Vals Index result, 53.8%.
Directional only
Long documents
Listed context window
GPT-5.4
GPT-5.4 takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiniMax M3.1 Flash
GPT-5.4 $0.010, MiniMax M3.1 Flash $0.0004 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5.4 has the number, $1.02.
Directional only
At a glance
- Coding index
- GPT-5.4 64.4 from 3 benchmarks, MiniMax M3.1 Flash 59.0 from 4 benchmarks.
- Widest category
- Coding, 14.3 points apart on average over 4 shared benchmarks.
- Widest single gap
- LMArena WebDev: React: GPT-5.4 1454 against MiniMax M3.1 Flash 1609, 24.4 points apart on a 0 to 100 scale.
- Output price
- GPT-5.4 $15.00 against MiniMax M3.1 Flash $0.60 per million output tokens, 25.0x apart.
- Context window
- GPT-5.4 takes 1.05M tokens, MiniMax M3.1 Flash 1M.
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 | Bars | MiniMax M3.1 Flash | Ties |
|---|---|---|---|---|
| Coding | 0 | 4 | ||
| Intelligence | 0 | 1 | ||
| Reasoning | 0 | 1 | ||
| General | 1 | 0 | ||
| All shared boards | 1 | 6 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
| Benchmark | GPT-5.4 | MiniMax M3.1 Flash | Leader |
|---|---|---|---|
| LiveBench coding | Not measured | 83.9% | Only MiniMax M3.1 Flash measured |
| LMArena WebDev | 1464 | 1587 | MiniMax M3.1 Flash |
| AA Coding Index | 71.1 | Not measured | Only GPT-5.4 measured |
| LiveCodeBench (Vals AI) | 84.1% | Not measured | Only GPT-5.4 measured |
| SWE-bench Verified (Vals AI) | 78.2% | Not measured | Only GPT-5.4 measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 25.3% | Only MiniMax M3.1 Flash measured |
| Vibe Code Bench (Vals AI) | 67.4% | 73.9% | MiniMax M3.1 Flash |
| Code migration (Vals AI) | 35.0% | Not measured | Only GPT-5.4 measured |
| ProgramBench (Vals AI) | 0.5% | Not measured | Only GPT-5.4 measured |
| SkillsBench (Vals AI) | 51.7% | Not measured | Only GPT-5.4 measured |
| SciCode | Not measured | 53.4% | Only MiniMax M3.1 Flash measured |
| Terminal-Bench Hard (Artificial Analysis run) | 57.6% | Not measured | Only GPT-5.4 measured |
| Terminal-Bench | 81.8% | Not measured | Only GPT-5.4 measured |
| GSO-Bench | 31.4% | Not measured | Only GPT-5.4 measured |
| WeirdML | 77.7% | Not measured | Only GPT-5.4 measured |
| MirrorCode | 15.6% | Not measured | Only GPT-5.4 measured |
| ALE-Bench | 1607.0 | Not measured | Only GPT-5.4 measured |
| LMArena Text: coding | 1496 | Not measured | Only GPT-5.4 measured |
| LMArena Text: software and IT | 1491 | Not measured | Only GPT-5.4 measured |
| LMArena WebDev: React | 1454 | 1609 | MiniMax M3.1 Flash |
| LMArena WebDev: HTML | 1478 | 1529 | MiniMax M3.1 Flash |
| LMArena WebDev: from an image | 1436 | Not measured | Only GPT-5.4 measured |
| SWE Atlas: Codebase QnA | 40.8% | Not measured | Only GPT-5.4 measured |
| SWE Atlas: Refactoring | 44.3% | Not measured | Only GPT-5.4 measured |
| SWE Atlas: Test Writing | 44.4% | Not measured | Only GPT-5.4 measured |
| Neither model has a result on the other 18 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-5.4 | MiniMax M3.1 Flash | Leader |
|---|---|---|---|
| AA Intelligence Index | 39.0 | 42.7 | MiniMax M3.1 Flash |
| Epoch Capabilities Index | 157.3 | Not measured | Only GPT-5.4 measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index18 boards, none shared
| Benchmark | GPT-5.4 | MiniMax M3.1 Flash | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1059 | Not measured | Only GPT-5.4 measured |
| Design Arena: agents building full-stack apps | 1017 | Not measured | Only GPT-5.4 measured |
| Design Arena: agents building mobile apps | 1086 | Not measured | Only GPT-5.4 measured |
| Design Arena: agents building Android apps | 1031 | Not measured | Only GPT-5.4 measured |
| Design Arena: agents building Godot games | 1135 | Not measured | Only GPT-5.4 measured |
| LiveBench research | Not measured | 72.7% | Only MiniMax M3.1 Flash measured |
| LiveBench browser | Not measured | 92.0% | Only MiniMax M3.1 Flash measured |
| LiveBench long agentic | Not measured | 34.7% | Only MiniMax M3.1 Flash measured |
| Tax Agent Bench (Vals AI) | Not measured | 32.1% | Only MiniMax M3.1 Flash measured |
| Legal Research Bench (Vals AI) | Not measured | 34.1% | Only MiniMax M3.1 Flash measured |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 7.5% | Only MiniMax M3.1 Flash measured |
| τ²-Bench Telecom | 87.1% | Not measured | Only GPT-5.4 measured |
| APEX-Agents | 52.4% | Not measured | Only GPT-5.4 measured |
| METR time horizons | 74.3% | Not measured | Only GPT-5.4 measured |
| DeepResearch Bench | 35.1% | Not measured | Only GPT-5.4 measured |
| PostTrainBench | 19.0% | Not measured | Only GPT-5.4 measured |
| Vending-Bench 2 | $6,144 | Not measured | Only GPT-5.4 measured |
| MCP Atlas | 70.6% | Not measured | Only GPT-5.4 measured |
| Neither model has a result on the other 24 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-5.4 | MiniMax M3.1 Flash | Leader |
|---|---|---|---|
| GPQA Diamond | 91.7% | Not measured | Only GPT-5.4 measured |
| LiveBench reasoning | Not measured | 82.9% | Only MiniMax M3.1 Flash measured |
| MMMU Pro (Vals AI) | 87.5% | Not measured | Only GPT-5.4 measured |
| GPQA Diamond (Artificial Analysis run) | 92.0% | Not measured | Only GPT-5.4 measured |
| Humanity's Last Exam (Artificial Analysis run) | 43.7% | 48.0% | MiniMax M3.1 Flash |
| GPQA Diamond (Epoch AI run) | 93.3% | Not measured | Only GPT-5.4 measured |
| ARC-AGI | 93.7% | Not measured | Only GPT-5.4 measured |
| ARC-AGI-2 | 74.0% | Not measured | Only GPT-5.4 measured |
| Chess puzzles | 48.0% | Not measured | Only GPT-5.4 measured |
| Mystery game puzzles | 37.0% | Not measured | Only GPT-5.4 measured |
| EBR-bench | 25.4% | Not measured | Only GPT-5.4 measured |
| LMArena Text: hard prompts | 1485 | Not measured | Only GPT-5.4 measured |
| LMArena Text: expert | 1507 | Not measured | Only GPT-5.4 measured |
| LMArena Text: hard prompts in English | 1479 | Not measured | Only GPT-5.4 measured |
| LMArena Vision: diagrams | 1327 | Not measured | Only GPT-5.4 measured |
| LMArena Vision: homework | 1336 | Not measured | Only GPT-5.4 measured |
| Kagi LLM Benchmark | 63.8% | Not measured | Only GPT-5.4 measured |
| Neither model has a result on the other 6 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | GPT-5.4 | MiniMax M3.1 Flash | Leader |
|---|---|---|---|
| AIME | 96.7% | Not measured | Only GPT-5.4 measured |
| OTIS Mock AIME | 97.8% | Not measured | Only GPT-5.4 measured |
| FrontierMath, tiers 1 to 3 | 78.6% | Not measured | Only GPT-5.4 measured |
| FrontierMath, tier 4 | 49.0% | Not measured | Only GPT-5.4 measured |
| ProofBench | 56.0% | Not measured | Only GPT-5.4 measured |
| LMArena Text: math | 1488 | Not measured | Only GPT-5.4 measured |
| LMArena Text: mathematical work | 1497 | Not measured | Only GPT-5.4 measured |
| MathArena | 37.2% | Not measured | Only GPT-5.4 measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index15 boards, none shared
| Benchmark | GPT-5.4 | MiniMax M3.1 Flash | Leader |
|---|---|---|---|
| MMLU Pro | 87.5% | Not measured | Only GPT-5.4 measured |
| LegalBench (Vals AI) | 86.0% | Not measured | Only GPT-5.4 measured |
| CaseLaw (Vals AI) | 63.8% | Not measured | Only GPT-5.4 measured |
| CorpFin (Vals AI) | 65.3% | Not measured | Only GPT-5.4 measured |
| TaxEval (Vals AI) | 74.0% | Not measured | Only GPT-5.4 measured |
| MortgageTax (Vals AI) | 68.3% | Not measured | Only GPT-5.4 measured |
| MedQA (Vals AI) | 96.1% | Not measured | Only GPT-5.4 measured |
| MedCode (Vals AI) | 41.3% | Not measured | Only GPT-5.4 measured |
| SimpleQA Verified | 45.1% | Not measured | Only GPT-5.4 measured |
| LMArena Text: science | 1479 | Not measured | Only GPT-5.4 measured |
| LMArena Text: medicine and healthcare | 1458 | Not measured | Only GPT-5.4 measured |
| LMArena Text: legal and government | 1486 | Not measured | Only GPT-5.4 measured |
| LMArena Text: business and finance | 1474 | Not measured | Only GPT-5.4 measured |
| PRBench Finance | 45.6% | Not measured | Only GPT-5.4 measured |
| PRBench Legal | 44.4% | Not measured | Only GPT-5.4 measured |
| Neither model has a result on the other 5 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | GPT-5.4 | MiniMax M3.1 Flash | Leader |
|---|---|---|---|
| Design Arena: websites | 1198 | Not measured | Only GPT-5.4 measured |
| Design Arena: UI components | 1213 | Not measured | Only GPT-5.4 measured |
| Design Arena: game dev | 1194 | Not measured | Only GPT-5.4 measured |
| Design Arena: data viz | 1196 | Not measured | Only GPT-5.4 measured |
| Design Arena: 3D | 1065 | Not measured | Only GPT-5.4 measured |
| Design Arena: all code categories | 1179 | Not measured | Only GPT-5.4 measured |
| Design Arena: SVG | 1141 | Not measured | Only GPT-5.4 measured |
| Design Arena: ASCII art | 1188 | Not measured | Only GPT-5.4 measured |
| LiveBench design | Not measured | 74.0% | Only MiniMax M3.1 Flash measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-5.4 | MiniMax M3.1 Flash | Leader |
|---|---|---|---|
| Vals Index | Not measured | 53.8% | Only MiniMax M3.1 Flash measured |
| LiveBench data analysis | Not measured | 71.4% | Only MiniMax M3.1 Flash measured |
| SAGE (Vals AI) | 43.3% | Not measured | Only GPT-5.4 measured |
| MedScribe (Vals AI) | 77.5% | Not measured | Only GPT-5.4 measured |
| IFBench | 73.9% | Not measured | Only GPT-5.4 measured |
| Long context reasoning (AA-LCR) | 82.0% | 79.7% | GPT-5.4 |
| DTBench | 94.4% | Not measured | Only GPT-5.4 measured |
| LMCA | 52.0% | Not measured | Only GPT-5.4 measured |
| CL-bench | 27.9% | Not measured | Only GPT-5.4 measured |
| Furniture assembly | 37.5% | Not measured | Only GPT-5.4 measured |
| CL-bench Life | 21.7% | Not measured | Only GPT-5.4 measured |
| LMArena Text | 1469 | Not measured | Only GPT-5.4 measured |
| LMArena Text: instruction following | 1469 | Not measured | Only GPT-5.4 measured |
| LMArena Text: creative writing | 1439 | Not measured | Only GPT-5.4 measured |
| LMArena Vision | 1303 | Not measured | Only GPT-5.4 measured |
| LMArena Text: English | 1467 | Not measured | Only GPT-5.4 measured |
| LMArena Text: non-English | 1465 | Not measured | Only GPT-5.4 measured |
| LMArena Text: Chinese | 1520 | Not measured | Only GPT-5.4 measured |
| LMArena Text: German | 1472 | Not measured | Only GPT-5.4 measured |
| LMArena Text: Japanese | 1485 | Not measured | Only GPT-5.4 measured |
| LMArena Text: Korean | 1449 | Not measured | Only GPT-5.4 measured |
| LMArena Text: French | 1493 | Not measured | Only GPT-5.4 measured |
| LMArena Text: Spanish | 1452 | Not measured | Only GPT-5.4 measured |
| LMArena Text: Russian | 1480 | Not measured | Only GPT-5.4 measured |
| LMArena Text: Polish | 1472 | Not measured | Only GPT-5.4 measured |
| LMArena Text: multi-turn | 1482 | Not measured | Only GPT-5.4 measured |
| LMArena Text: longer queries | 1473 | Not measured | Only GPT-5.4 measured |
| LMArena Text: writing and language | 1458 | Not measured | Only GPT-5.4 measured |
| LMArena Text: entertainment and media | 1438 | Not measured | Only GPT-5.4 measured |
| LMArena Vision: English | 1301 | Not measured | Only GPT-5.4 measured |
| LMArena Vision: Chinese | 1354 | Not measured | Only GPT-5.4 measured |
| LMArena Vision: reading text | 1312 | Not measured | Only GPT-5.4 measured |
| LMArena Vision: humor | 1284 | Not measured | Only GPT-5.4 measured |
| LMArena Vision: recognizing things | 1251 | Not measured | Only GPT-5.4 measured |
| LMArena Vision: creative writing | 1283 | Not measured | Only GPT-5.4 measured |
| LMArena Document | 1471 | Not measured | Only GPT-5.4 measured |
| EQ-Bench 4 | 1272 | Not measured | Only GPT-5.4 measured |
| Neither model has a result on the other 11 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.4 | MiniMax M3.1 Flash | 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
MiniMax M3.1 Flash costs less
Repository review
50K input + 3K output tokens
MiniMax M3.1 Flash costs less
Agent loop
200K input + 10K output tokens
MiniMax M3.1 Flash 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 | MiniMax M3.1 Flash |
|---|---|---|
| Maker | OpenAI | MiniMax |
| Weights | No public weights listed | No public weights listed |
| Released | March 5, 2026 | October 19, 2026 |
| Context window | 1.05M | 1M |
| Input $/Mtok | $2.50 | $0.15 |
| Output $/Mtok | $15.00 | $0.60 |
| Coding index | 64.4 | 59.0 |
| Independent measurements behind it | 3 | 4 |
| Cost per solved task | $1.02 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.4 better than MiniMax M3.1 Flash for coding?
Pick GPT-5.4 for coding: it scores 64.4 on the Vibe Coding Index against 59.0 for MiniMax M3.1 Flash, though on 3 benchmarks against 4. Pick MiniMax M3.1 Flash for output tokens 25.0x cheaper ($0.60 vs $15.00 per million) and work measured by LMArena WebDev or Vibe Code Bench (Vals AI), where it leads.
Which is cheaper, GPT-5.4 or MiniMax M3.1 Flash?
GPT-5.4 costs $2.50 per million input tokens and $15.00 per million output tokens; MiniMax M3.1 Flash costs $0.15 and $0.60. Cost per solved task is known for GPT-5.4 only.
Which has the bigger context window, GPT-5.4 or MiniMax M3.1 Flash?
GPT-5.4, with 1.05M tokens against 1M.
How many benchmarks is the GPT-5.4 vs MiniMax M3.1 Flash comparison based on?
7 benchmarks have a result for both models as of October 22, 2026. GPT-5.4's coding index rests on 3 independent benchmarks and MiniMax M3.1 Flash's on 4. Where only one model has a result, the page says so instead of naming a winner.