Model comparison
GPT-5.4 vs MiMo-V2.5
Head-to-head evidence from 8 shared benchmark results across 3 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: GPT-5.4 #8 (Supported); MiMo-V2.5 #62 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GPT-5.4 and MiMo-V2.5 share 8 comparable benchmark results. 3 of 8 categories are comparable. 44 results are unique to GPT-5.4; 3 to MiMo-V2.5.
Updated July 21, 2026- Shared results
- 8
- GPT-5.4 only
- 44
- MiMo-V2.5 only
- 3
- Comparable categories
- 3 / 8
Pick GPT-5.4 if you want the stronger benchmark profile. MiMo-V2.5 only becomes the better choice if multimodal & grounded is the priority.
Confidence note. This is a partial-evidence comparison with 8 shared benchmark results across 3 evidence categories; 3 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
GPT-5.4 is clearly ahead on the BenchAlign aggregate, 74.24 to 58.62. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-5.4's sharpest advantage is in agentic, where it averages 77.2 against 65.8. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 75.1% to 65.8%. MiMo-V2.5 does hit back in multimodal & grounded, so the answer changes if that is the part of the workload you care about most.
GPT-5.4 gives you the larger context window at 1.05M, compared with 1M for MiMo-V2.5.
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 | Δ | MiMo-V2.5 |
|---|---|---|---|
| Agentic | GPT-5.477.2 | Margin← 11.4 | MiMo-V2.565.8 |
| Multimodal | GPT-5.473.2 | Margin→ 5.8 | MiMo-V2.579.0 |
| Coding | GPT-5.457.7 | Margin← 1.6 | MiMo-V2.556.1 |
| Knowledge | GPT-5.457.6 | MarginNo overlap | MiMo-V2.5Not measured |
| Math | GPT-5.442.5 | MarginNo overlap | MiMo-V2.5Not measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
Terminal-Bench 2.0
AgenticA 75.1%B 65.8%Winner: GPT-5.4Δ 9.3Terminal-Bench 2.0: GPT-5.4 scored 75.1%; MiMo-V2.5 scored 65.8%. GPT-5.4 wins this benchmark. - Source ↗
MMMU-Pro
MultimodalA 81.2%B 77.9%Winner: GPT-5.4Δ 3.3MMMU-Pro: GPT-5.4 scored 81.2%; MiMo-V2.5 scored 77.9%. GPT-5.4 wins this benchmark. - Source ↗
CharXiv
MultimodalA 82.8%B 81%Winner: GPT-5.4Δ 1.8CharXiv: GPT-5.4 scored 82.8%; MiMo-V2.5 scored 81%. GPT-5.4 wins this benchmark. - Source ↗
SWE-bench Pro
CodingA 57.7%B 56.1%Winner: GPT-5.4Δ 1.6SWE-bench Pro: GPT-5.4 scored 57.7%; MiMo-V2.5 scored 56.1%. GPT-5.4 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GPT-5.4 | MiMo-V2.5 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GPT-5.4$2.5 input / $15 output | MiMo-V2.5Not available | A complete price comparison is not available. |
| Generation speedtokens per second | GPT-5.474 tok/s | MiMo-V2.5Not available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | GPT-5.4151.79 s | MiMo-V2.5Not available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | GPT-5.41.05M | MiMo-V2.51M | GPT-5.4 lists the larger context window. |
Benchmark Deep Dive
AgenticGPT-5.4 wins18 benchmarks
| Benchmark | GPT-5.4 | MiMo-V2.5 | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 75.1% | 65.8% | GPT-5.4 leads |
| CyberGymSource | 79.0% | — | Not comparable |
| BrowseCompSource | 82.7% | — | Not comparable |
| OSWorld-VerifiedSource | 75% | — | Not comparable |
| MCP AtlasSource | 70.6% | — | Not comparable |
| ToolathlonSource | 54.6% | — | Not comparable |
| τ²-bench resultsSource | 87.1% | — | Not comparable |
| Claw-EvalSource | 60.3% | 62.3% | MiMo-V2.5 leads |
| DeepSearchQASource | 73.6% | — | Not comparable |
| AA Agentic IndexSource | 41.1% | — | Not comparable |
| APEX-Agents-AASource | 33.3% | — | Not comparable |
| GDPval-AASource | 44.7% | — | Not comparable |
| GDPval-AASource | 1395 | — | Not comparable |
| Gert LabsSource | 64.89% | 46.89% | GPT-5.4 leads |
| ResearchClawBenchSource | 15.3% | 16.9% | MiMo-V2.5 leads |
| JobBenchSource | 38.9% | — | Not comparable |
| ExploitGymSource | 6.0% | — | Not comparable |
| MM-ClawBenchSource | — | 23.8% | Not comparable |
CodingGPT-5.4 wins7 benchmarks
| Benchmark | GPT-5.4 | MiMo-V2.5 | Result |
|---|---|---|---|
| LiveCodeBench ProSource | 87.5% | — | Not comparable |
| SWE-bench ProSource | 57.7% | 56.1% | GPT-5.4 leads |
| React Native EvalsSource | 85.3% | — | Not comparable |
| Vibe Code BenchSource | 67.42% | — | Not comparable |
| AA Coding IndexSource | 71.0% | — | Not comparable |
| AA-SciCodeSource | 56.6% | — | Not comparable |
| Terminal-Bench 2.0Source | — | 65.8% | Not comparable |
Reasoning2 benchmarks
Knowledge13 benchmarks
| Benchmark | GPT-5.4 | MiMo-V2.5 | Result |
|---|---|---|---|
| GPQASource | 92.8% | — | Not comparable |
| HLESource | 52.1% | — | Not comparable |
| HLE w/o toolsSource | 39.8% | — | Not comparable |
| GPQA-DSource | 92.8% | — | Not comparable |
| HealthBench HardSource | 40.1% | — | Not comparable |
| MedXpertQA (Text)Source | 59.6% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 51.4% | — | Not comparable |
| AA-GPQA DiamondSource | 92.0% | — | Not comparable |
| AA-HLESource | 41.6% | — | Not comparable |
| AA-Omniscience IndexSource | 5.7% | — | Not comparable |
| AA-Omniscience AccuracySource | 50.0% | — | Not comparable |
| AA-Omniscience Hallucination RateSource | 88.6% | — | Not comparable |
| HealthBench ProfessionalSource | 48.1% | — | Not comparable |
Math2 benchmarks
MultimodalMiMo-V2.5 wins12 benchmarks
| Benchmark | GPT-5.4 | MiMo-V2.5 | Result |
|---|---|---|---|
| MMMU-ProSource | 81.2% | 77.9% | GPT-5.4 leads |
| OfficeQA ProSource | 53.2% | — | Not comparable |
| MMMU-Pro w/ PythonSource | 82.1% | — | Not comparable |
| CharXivSource | 82.8% | 81% | GPT-5.4 leads |
| ERQASource | 65.4% | — | Not comparable |
| SimpleVQASource | 61.1% | — | Not comparable |
| ScreenSpot ProSource | 85.4% | — | Not comparable |
| ZeroBenchSource | 41.0% | — | Not comparable |
| MedXpertQA (MM)Source | 77.1% | — | Not comparable |
| AA-MMMU-ProSource | 78.4% | — | Not comparable |
| Design Arena WebsiteSource | 1250 | 1291 | MiMo-V2.5 leads |
| Video-MME (with subtitle)Source | — | 87.7% | Not comparable |
Inst. Following1 benchmarks
| Benchmark | GPT-5.4 | MiMo-V2.5 | Result |
|---|---|---|---|
| AA-IFBenchSource | 73.9% | — | Not comparable |
Frequently Asked Questions (4)
Which is better, GPT-5.4 or MiMo-V2.5?
GPT-5.4 is ahead on BenchLM's BenchAlign leaderboard, 74.24 to 58.62. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 75.1% and 65.8%.
Which is better for coding, GPT-5.4 or MiMo-V2.5?
GPT-5.4 has the edge for coding in this comparison, averaging 57.7 versus 56.1. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, GPT-5.4 or MiMo-V2.5?
GPT-5.4 has the edge for agentic tasks in this comparison, averaging 77.2 versus 65.8. Inside this category, Gert Labs is the benchmark that creates the most daylight between them.
Which is better for multimodal and grounded tasks, GPT-5.4 or MiMo-V2.5?
MiMo-V2.5 has the edge for multimodal and grounded tasks in this comparison, averaging 79 versus 73.2. Inside this category, Design Arena Website 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.