Model comparison
Composer 2.5 vs MiniMax M3
Head-to-head evidence from 2 shared benchmark results across 2 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Verified leaderboard positions: Composer 2.5 unranked; MiniMax M3 #18
BenchAlign evidence: Composer 2.5 not scored; MiniMax M3 supported. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Composer 2.5 and MiniMax M3 share 2 comparable benchmark results. 1 of 8 categories are comparable. 3 results are unique to Composer 2.5; 43 to MiniMax M3.
Updated July 16, 2026- Shared results
- 2
- Composer 2.5 only
- 3
- MiniMax M3 only
- 43
- Comparable categories
- 1 / 8
Pick MiniMax M3 if you want the stronger benchmark profile. Composer 2.5 only becomes the better choice if you want the stronger reasoning-first profile.
Confidence note. This is a partial-evidence comparison with 2 shared benchmark results across 2 evidence categories; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
MiniMax M3 is clearly ahead on the provisional aggregate, 70 to 63. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
MiniMax M3's sharpest advantage is in agentic, where it averages 72.3 against 69.3. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 69.3% to 66%.
Composer 2.5 is also the more expensive model on tokens at $0.50 input / $2.50 output per 1M tokens, versus $0.30 input / $1.20 output per 1M tokens for MiniMax M3. That is roughly 2.1x on output cost alone. Composer 2.5 is the reasoning model in the pair, while MiniMax M3 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. MiniMax M3 gives you the larger context window at 1M, compared with 200K for Composer 2.5.
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 | Composer 2.5 | Δ | MiniMax M3 |
|---|---|---|---|
| Agentic | Composer 2.569.3 | Margin→ 3.0 | MiniMax M372.3 |
| Coding | Composer 2.5Not measured | MarginNo overlap | MiniMax M372.2 |
| Math | Composer 2.5Not measured | MarginNo overlap | MiniMax M385.7 |
| Multimodal | Composer 2.5Not measured | MarginNo overlap | MiniMax M364.9 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
Terminal-Bench 2.0
AgenticA 69.3%B 66%Winner: Composer 2.5Δ 3.3Terminal-Bench 2.0: Composer 2.5 scored 69.3%; MiniMax M3 scored 66%. Composer 2.5 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Composer 2.5 | MiniMax M3 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Composer 2.5$0.5 input / $2.5 output | MiniMax M3$0.3 input / $1.2 output | MiniMax M3 has the lower combined listed price. |
| Generation speedtokens per second | Composer 2.5Not available | MiniMax M3Not available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Composer 2.5Not available | MiniMax M3Not available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Composer 2.5200K | MiniMax M31M | MiniMax M3 lists the larger context window. |
Benchmark Deep Dive
AgenticMiniMax M3 wins16 benchmarks
| Benchmark | Composer 2.5 | MiniMax M3 | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 69.3% | 66% | Composer 2.5 leads |
| BrowseCompSource | — | 83.5% | Not comparable |
| OSWorld-VerifiedSource | — | 70.1% | Not comparable |
| MCP AtlasSource | — | 74.2% | Not comparable |
| Claw-EvalSource | — | 74.5% | Not comparable |
| AA Agentic IndexSource | — | 35.4% | Not comparable |
| τ²-bench resultsSource | — | 88.9% | Not comparable |
| GDPval-AASource | — | 44.7% | Not comparable |
| GDPval-AASource | — | 1395 | Not comparable |
| GDPval rubricsSource | — | 74.7% | Not comparable |
| BankerToolBenchSource | — | 76.1% | Not comparable |
| ResearchClawBenchSource | — | 19.8% | Not comparable |
| OSWorld 2.0Source | — | 4.6% | Not comparable |
| AA BriefcaseSource | — | 1110 | Not comparable |
| AA EnterpriseOps-GymSource | — | 32.1% | Not comparable |
| AA Harvey LABSource | — | 6.7% | Not comparable |
Coding14 benchmarks
| Benchmark | Composer 2.5 | MiniMax M3 | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 69.3% | 66.0% | Composer 2.5 leads |
| SWE MultilingualSource | 79.8% | — | Not comparable |
| cursorBench31Source | 63.2% | — | Not comparable |
| cursorBench32Source | 56.1% | — | Not comparable |
| SWE-bench VerifiedSource | — | 80.5% | Not comparable |
| SWE-bench ProSource | — | 59% | Not comparable |
| NL2RepoSource | — | 42.1% | Not comparable |
| AA Coding IndexSource | — | 58.6% | Not comparable |
| Terminal-Bench HardSource | — | 42.4% | Not comparable |
| AA-SciCodeSource | — | 45.4% | Not comparable |
| VIBE V2Source | — | 50.1% | Not comparable |
| SVG-BenchSource | — | 63.7% | Not comparable |
| KernelBench HardSource | — | 28.8% | Not comparable |
| AA Terminal-Bench 2.1Source | — | 65.2% | Not comparable |
Reasoning2 benchmarks
Knowledge7 benchmarks
| Benchmark | Composer 2.5 | MiniMax M3 | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | — | 44.4% | Not comparable |
| AA-GPQA DiamondSource | — | 92.9% | Not comparable |
| AA-HLESource | — | 37.1% | Not comparable |
| AA-Omniscience IndexSource | — | 1.4% | Not comparable |
| AA-Omniscience AccuracySource | — | 15.0% | Not comparable |
| AA-Omniscience Hallucination RateSource | — | 16.1% | Not comparable |
| AA Openness IndexSource | — | 33.3% | Not comparable |
Math1 benchmarks
| Benchmark | Composer 2.5 | MiniMax M3 | Result |
|---|---|---|---|
| USAMO 2026Source | — | 85.7% | Not comparable |
Multimodal7 benchmarks
| Benchmark | Composer 2.5 | MiniMax M3 | Result |
|---|---|---|---|
| OfficeQA ProSource | — | 45.1% | Not comparable |
| OmniDocBench 1.5Source | — | 91.6% | Not comparable |
| MMMU-ProSource | — | 78.1% | Not comparable |
| VideoMMMUSource | — | 84.6% | Not comparable |
| Video-MME (with subtitle)Source | — | 85.4% | Not comparable |
| Design Arena WebsiteSource | — | 1294 | Not comparable |
| AA-MMMU-ProSource | — | 78.6% | Not comparable |
Inst. Following1 benchmarks
| Benchmark | Composer 2.5 | MiniMax M3 | Result |
|---|---|---|---|
| AA-IFBenchSource | — | 82.9% | Not comparable |
Frequently Asked Questions (2)
Which is better, Composer 2.5 or MiniMax M3?
MiniMax M3 is ahead on BenchLM's provisional leaderboard, 70 to 63. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 69.3% and 66%.
Which is better for agentic tasks, Composer 2.5 or MiniMax M3?
MiniMax M3 has the edge for agentic tasks in this comparison, averaging 72.3 versus 69.3. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
The AI models change fast. We track them for you.
A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.