Across 1 comparable benchmark, MiniCPM5-2B has better reported results on 1 and worse on 0.
Limited evidence1 of 1 shared result countedHow we compare
Price basis: Listed rates vs listed rates. The price section below shows the applicable periods.
| Fact | Llama3-70B-Instruct | MiniCPM5-2B |
|---|---|---|
| Context window | 8K tokens | 128K tokens |
| Input / 1M | $2.65 | — |
| Output / 1M | $3.50 | — |
| Blended (4:1) | $2.82 | — |
| Status | Available | Available |
| Released | April 18, 2024 | September 7, 2026 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Published scores, with matching modes where available. Gaps show Llama3-70B-Instruct relative to MiniCPM5-2B. Reading the results
| Benchmark | Llama3-70B-Instruct | MiniCPM5-2B | Gap |
|---|---|---|---|
| MMLU-ProKnowledge Exams · Accuracy | 56.2Normal · no tools | 70.8≠Reported best | −14.6 pts#117 vs #91 of 153 |
Knowledge Exams · Accuracy
A dash means no result is available.
| Benchmark | Llama3-70B-Instruct | MiniCPM5-2B |
|---|---|---|
| AIME 2026 | — | 86.5 |
| AIME2025 | — | 86.5 |
| CritPt | — | 0.3 |
| GPQA Diamond | — | 70.2 |
| HLE | — | 8.9 |
| HMMT Feb 2026 | — | 63.8 |
| MATH-500 | — | 94.6 |
| SciCode | — | 26.3 |
| LiveCodeBench | — | 69.1 |
| SWE-Bench Pro - Public | — | 14.4 |
| SWE-bench Verified | — | 46.4 |
| Terminal-Bench 2.1 | — | 8.6 |
| BFCL-V4 | — | 66.6 |
| IF Bench | — | 66.3 |
| IFEval | — | 86.7 |
| LongBench v2 | — | 43.7 |
| GDP.pdf | — | 1.4 |
| τ²-Bench - Telecom | — | 97.1 |
| τ³-Banking | — | 20.8 |
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
A blended cost needs a published input and output price on both sides, and one of these two does not have them yet.
Llama3-70B-Instruct: Listed text rates; pricing tier not confirmed.
MiniCPM5-2B: Listed text rates; pricing tier not confirmed.
| Price / 1M tokens | Llama3-70B-Instruct | MiniCPM5-2B | Ratio |
|---|---|---|---|
| Input | $2.65 | — | — |
| Output | $3.50 | — | — |
| Cached input | — | — | — |
| Cache write | — | — | — |
| Blended | $2.82 | — | — |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Lower prices are highlighted. The cache hit rate applies to input tokens only; models without a published cached-input rate use their normal input price for those tokens.Effective dates: Llama3-70B-Instruct 2026-11-14; MiniCPM5-2B —.| Attribute | Llama3-70B-Instruct | MiniCPM5-2B |
|---|---|---|
| Availability | Available | Available |
| Provider | Facebook AI Research Lab | OpenBMB |
| Model type | Chat model | Reasoning model |
| First release | April 18, 2024 | September 7, 2026 |
| Context window | 8K tokens | 128K tokens |
| Total parameters | 70B | 2.5B |
| Active parameters | — | 2.5B |
| Architecture | Dense | Dense |
| Documented capabilities | — | Reasoning, Multilingual, Coding, Function calling, Tool use, Web search, Long context |
| Input modalities | — | Text |
| Output modalities | — | Text |
| Weights | Open weights | Open weights |
| Licence | META LLAMA 3 COMMUNITY LICENSE AGREEMENT | Apache 2.0 |
| Commercial use | Commercial use allowed | Commercial use allowed |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used Llama3-70B-Instruct or MiniCPM5-2B? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.