Model comparison
GPT-5.4 mini vs MiMo-V2.5-Pro
Head-to-head evidence from 19 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: GPT-5.4 mini #75 (Estimated); MiMo-V2.5-Pro #14 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GPT-5.4 mini and MiMo-V2.5-Pro share 19 comparable benchmark results. 2 of 8 categories are comparable. 11 results are unique to GPT-5.4 mini; 12 to MiMo-V2.5-Pro.
Updated July 21, 2026- Shared results
- 19
- GPT-5.4 mini only
- 11
- MiMo-V2.5-Pro only
- 12
- Comparable categories
- 2 / 8
Pick MiMo-V2.5-Pro if you want the stronger benchmark profile. GPT-5.4 mini only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.
Confidence note. This is a partial-evidence comparison with 19 shared benchmark results across 5 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
MiMo-V2.5-Pro is clearly ahead on the BenchAlign aggregate, 70.19 to 56.77. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
MiMo-V2.5-Pro's sharpest advantage is in agentic, where it averages 68.4 against 65.7. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 60% to 68.4%.
MiMo-V2.5-Pro gives you the larger context window at 1M, compared with 400K for GPT-5.4 mini.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | GPT-5.4 mini | Δ | MiMo-V2.5-Pro |
|---|---|---|---|
| Agentic | GPT-5.4 mini65.7 | Margin→ 2.7 | MiMo-V2.5-Pro68.4 |
| Knowledge | GPT-5.4 mini47.8 | Margin→ 0.2 | MiMo-V2.5-Pro48.0 |
| Coding | GPT-5.4 miniNot measured | MarginNo overlap | MiMo-V2.5-Pro57.2 |
| Math | GPT-5.4 mini21.7 | MarginNo overlap | MiMo-V2.5-ProNot measured |
| Multimodal | GPT-5.4 mini76.6 | MarginNo overlap | MiMo-V2.5-ProNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
Terminal-Bench 2.0
AgenticA 60%B 68.4%Winner: MiMo-V2.5-ProΔ 8.4Terminal-Bench 2.0: GPT-5.4 mini scored 60%; MiMo-V2.5-Pro scored 68.4%. MiMo-V2.5-Pro wins this benchmark. - Source ↗
HLE
KnowledgeA 41.5%B 48%Winner: MiMo-V2.5-ProΔ 6.5HLE: GPT-5.4 mini scored 41.5%; MiMo-V2.5-Pro scored 48%. MiMo-V2.5-Pro wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GPT-5.4 mini | MiMo-V2.5-Pro | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GPT-5.4 mini$0.75 input / $4.5 output | MiMo-V2.5-ProNot available | A complete price comparison is not available. |
| Generation speedtokens per second | GPT-5.4 mini201 tok/s | MiMo-V2.5-ProNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | GPT-5.4 mini3.85 s | MiMo-V2.5-ProNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | GPT-5.4 mini400K | MiMo-V2.5-Pro1M | MiMo-V2.5-Pro lists the larger context window. |
Benchmark Deep Dive
AgenticMiMo-V2.5-Pro wins17 benchmarks
| Benchmark | GPT-5.4 mini | MiMo-V2.5-Pro | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 60% | 68.4% | MiMo-V2.5-Pro leads |
| OSWorld-VerifiedSource | 72.1% | — | Not comparable |
| MCP AtlasSource | 57.7% | — | Not comparable |
| ToolathlonSource | 42.9% | — | Not comparable |
| τ²-bench resultsSource | 83.3% | 94.2% | MiMo-V2.5-Pro leads |
| AA Agentic IndexSource | 30.2% | 29.1% | GPT-5.4 mini leads |
| APEX-Agents-AASource | 28.2% | 2.4% | GPT-5.4 mini leads |
| GDPval-AASource | 33.6% | 38.3% | MiMo-V2.5-Pro leads |
| GDPval-AASource | 1171 | 1265 | MiMo-V2.5-Pro leads |
| Claw-EvalSource | — | 63.8% | Not comparable |
| τ³-bench resultsSource | — | 72.9% | Not comparable |
| Gert LabsSource | — | 62.70% | Not comparable |
| AA BriefcaseSource | — | 873 | Not comparable |
| AA ITBenchSource | — | 38.2% | Not comparable |
| terminalBenchHardSource | — | 43.2% | Not comparable |
| aaTerminalBench21Source | — | 65.2% | Not comparable |
| AA Harvey LABSource | — | 73.3% | Not comparable |
Coding6 benchmarks
| Benchmark | GPT-5.4 mini | MiMo-V2.5-Pro | Result |
|---|---|---|---|
| Vibe Code BenchSource | 47.97% | — | Not comparable |
| AA Coding IndexSource | 56.1% | 60.2% | MiMo-V2.5-Pro leads |
| AA-SciCodeSource | 49.9% | 50.2% | MiMo-V2.5-Pro leads |
| FrontierCode 1.1 MainSource | 27.0% | — | Not comparable |
| SWE-bench ProSource | — | 57.2% | Not comparable |
| Terminal-Bench 2.0Source | — | 68.4% | Not comparable |
Reasoning2 benchmarks
KnowledgeMiMo-V2.5-Pro wins10 benchmarks
| Benchmark | GPT-5.4 mini | MiMo-V2.5-Pro | Result |
|---|---|---|---|
| GPQASource | 88% | — | Not comparable |
| HLESource | 41.5% | 48% | MiMo-V2.5-Pro leads |
| HLE w/o toolsSource | 28.2% | 34% | MiMo-V2.5-Pro leads |
| Artificial Analysis Intelligence IndexSource | 40.0% | 42.2% | MiMo-V2.5-Pro leads |
| AA-GPQA DiamondSource | 87.5% | 86.6% | GPT-5.4 mini leads |
| AA-HLESource | 26.6% | 33.8% | MiMo-V2.5-Pro leads |
| AA-Omniscience IndexSource | -18.7% | 3.6% | MiMo-V2.5-Pro leads |
| AA-Omniscience AccuracySource | 37.5% | 22.6% | GPT-5.4 mini leads |
| AA-Omniscience Hallucination RateSource | 89.8% | 24.5% | MiMo-V2.5-Pro leads |
| AA Openness IndexSource | — | 38.9% | Not comparable |
Math2 benchmarks
Multimodal4 benchmarks
Inst. Following1 benchmarks
| Benchmark | GPT-5.4 mini | MiMo-V2.5-Pro | Result |
|---|---|---|---|
| AA-IFBenchSource | 73.3% | 79.9% | MiMo-V2.5-Pro leads |
Frequently Asked Questions (3)
Which is better, GPT-5.4 mini or MiMo-V2.5-Pro?
MiMo-V2.5-Pro is ahead on BenchLM's BenchAlign leaderboard, 70.19 to 56.77. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 60% and 68.4%.
Which is better for knowledge tasks, GPT-5.4 mini or MiMo-V2.5-Pro?
MiMo-V2.5-Pro has the edge for knowledge tasks in this comparison, averaging 48 versus 47.8. Inside this category, AA-Omniscience Hallucination Rate is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, GPT-5.4 mini or MiMo-V2.5-Pro?
MiMo-V2.5-Pro has the edge for agentic tasks in this comparison, averaging 68.4 versus 65.7. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.