Across 3 comparable benchmarks, Baichuan 3 has better reported results on 3 and worse on 0.
Moderate evidence3 of 3 shared results countedHow we compare
Price basis: Listed rates vs listed rates. The price section below shows the applicable periods.
| Fact | Baichuan 3 | LLaMA 33B |
|---|---|---|
| Context window | 8K tokens | 2K tokens |
| Input / 1M | — | — |
| Output / 1M | — | — |
| Blended (4:1) | — | — |
| Status | Available | Available |
| Released | January 29, 2024 | February 24, 2023 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 1 shared benchmark grouped by capability on a 0–100 scale. How averages are built
Baichuan 3 ahead on 1 of 1 counted
No shared comparable results for Coding, Abstract reasoning, Science & health, Computer & tool use, Research & search, Long context, Multimodal, Professional work & productivity, Cybersecurity.
Published scores, with matching modes where available. Gaps show Baichuan 3 relative to LLaMA 33B. Reading the results
| Benchmark | Baichuan 3 | LLaMA 33B | Gap |
|---|---|---|---|
| GSM8KMathematics · Accuracy | 88.2Historical | 35.6Historical | +52.6 pts#18 vs #52 of 67 |
| AGIEvalKnowledge Exams · accuracy | 73.2Historical | 41.7Historical | +31.5 pts#1 vs #14 of 27 |
| MMLUKnowledge Exams · Accuracy | 81.7Historical | 57.8Historical | +23.9 pts#42 vs #86 of 114 |
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.
Baichuan 3: Listed text rates; pricing tier not confirmed.
LLaMA 33B: Listed text rates; pricing tier not confirmed.
| Price / 1M tokens | Baichuan 3 | LLaMA 33B | Ratio |
|---|---|---|---|
| Input | — | — | — |
| Output | — | — | — |
| Cached input | — | — | — |
| Cache write | — | — | — |
| Blended | — | — | — |
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.| Attribute | Baichuan 3 | LLaMA 33B |
|---|---|---|
| Availability | Available | Available |
| Provider | Baichuan Intelligence | Facebook AI Research Lab |
| Model type | Foundation model | Foundation model |
| First release | January 29, 2024 | February 24, 2023 |
| Context window | 8K tokens | 2K tokens |
| Total parameters | — | 33B |
| Architecture | Undisclosed | Dense |
| Documented capabilities | Multilingual | — |
| Weights | Closed / API only | Restricted weights |
| Commercial use | Proprietary | 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 Baichuan 3 or LLaMA 33B? 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.