Qwen2.5 72B Instruct vs Beam 1.0 501B A23B
Qwen2.5 72B Instruct costs 2.8x less per output token than Beam 1.0 501B A23B ($0.40 vs $1.10 per million). Updated October 22, 2026; 23 benchmarks have a result for both.
Qwen2.5 72B Instruct or Beam 1.0 501B A23B: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Qwen2.5 72B Instruct for output tokens 2.8x cheaper ($0.40 vs $1.10 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.
- Shared results
- 23
- Qwen2.5 72B Instruct only
- 30
- Beam 1.0 501B A23B only
- 5
- Like-for-like categories
- 5 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
No call
Only Qwen2.5 72B Instruct has a AA Intelligence Index result, 7.7.
Directional only
Web design
Design Arena: websites
No call
Only Beam 1.0 501B A23B has a Design Arena: websites result, 1250.
Directional only
Long documents
Listed context window
Beam 1.0 501B A23B
Beam 1.0 501B A23B takes 1.05M tokens against 33K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen2.5 72B Instruct
Qwen2.5 72B Instruct $0.0006, Beam 1.0 501B A23B $0.0009 per turn.
List prices
At a glance
- Coding index
- Qwen2.5 72B Instruct not benchmarked, Beam 1.0 501B A23B not benchmarked.
- Widest category
- Reasoning, 30.2 points apart on average over 3 shared benchmarks.
- Widest single gap
- LMArena Text: expert: Qwen2.5 72B Instruct 1245 against Beam 1.0 501B A23B 1447, 33.6 points apart on a 0 to 100 scale.
- Output price
- Qwen2.5 72B Instruct $0.40 against Beam 1.0 501B A23B $1.10 per million output tokens, 2.8x apart.
- Context window
- Qwen2.5 72B Instruct takes 33K tokens, Beam 1.0 501B A23B 1.05M.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Qwen2.5 72B Instruct | Bars | Beam 1.0 501B A23B | Ties |
|---|---|---|---|---|
| Coding | 0 | 2 | ||
| Reasoning | 0 | 3 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 4 | ||
| General | 0 | 12 | ||
| All shared boards | 0 | 23 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
| Benchmark | Qwen2.5 72B Instruct | Beam 1.0 501B A23B | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1437 | Only Beam 1.0 501B A23B measured |
| LiveCodeBench (Artificial Analysis run) | 27.6% | Not measured | Only Qwen2.5 72B Instruct measured |
| Terminal-Bench Hard (Artificial Analysis run) | 4.5% | Not measured | Only Qwen2.5 72B Instruct measured |
| WeirdML | 16.0% | Not measured | Only Qwen2.5 72B Instruct measured |
| LMArena Text: coding | 1292 | 1473 | Beam 1.0 501B A23B |
| LMArena Text: software and IT | 1292 | 1461 | Beam 1.0 501B A23B |
| LMArena WebDev: React | Not measured | 1443 | Only Beam 1.0 501B A23B measured |
| LMArena WebDev: HTML | Not measured | 1436 | Only Beam 1.0 501B A23B measured |
| Neither model has a result on the other 31 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Qwen2.5 72B Instruct | Beam 1.0 501B A23B | Leader |
|---|---|---|---|
| AA Intelligence Index | 7.7 | Not measured | Only Qwen2.5 72B Instruct measured |
| Epoch Capabilities Index | 129.0 | Not measured | Only Qwen2.5 72B Instruct measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | Qwen2.5 72B Instruct | Beam 1.0 501B A23B | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 34.5% | Not measured | Only Qwen2.5 72B Instruct measured |
| METR time horizons | 35.8% | Not measured | Only Qwen2.5 72B Instruct measured |
| BALROG | 16.2% | Not measured | Only Qwen2.5 72B Instruct measured |
| TheAgentCompany | 5.7% | Not measured | Only Qwen2.5 72B Instruct measured |
| Neither model has a result on the other 37 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | Qwen2.5 72B Instruct | Beam 1.0 501B A23B | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 49.1% | Not measured | Only Qwen2.5 72B Instruct measured |
| Humanity's Last Exam (Artificial Analysis run) | 3.6% | Not measured | Only Qwen2.5 72B Instruct measured |
| GPQA Diamond (Epoch AI run) | 49.1% | Not measured | Only Qwen2.5 72B Instruct measured |
| BIG-Bench Hard | 79.8% | Not measured | Only Qwen2.5 72B Instruct measured |
| LMArena Text: hard prompts | 1271 | 1442 | Beam 1.0 501B A23B |
| LMArena Text: expert | 1245 | 1447 | Beam 1.0 501B A23B |
| LMArena Text: hard prompts in English | 1279 | 1451 | Beam 1.0 501B A23B |
| Neither model has a result on the other 15 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Qwen2.5 72B Instruct | Beam 1.0 501B A23B | Leader |
|---|---|---|---|
| AA Math Index | 14.0 | Not measured | Only Qwen2.5 72B Instruct measured |
| AIME 2025 (Artificial Analysis run) | 14.0% | Not measured | Only Qwen2.5 72B Instruct measured |
| OTIS Mock AIME | 8.1% | Not measured | Only Qwen2.5 72B Instruct measured |
| MATH level 5 | 63.2% | Not measured | Only Qwen2.5 72B Instruct measured |
| LMArena Text: math | 1283 | 1459 | Beam 1.0 501B A23B |
| LMArena Text: mathematical work | 1290 | 1475 | Beam 1.0 501B A23B |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Qwen2.5 72B Instruct | Beam 1.0 501B A23B | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 72.0% | Not measured | Only Qwen2.5 72B Instruct measured |
| MMLU | 85.3% | Not measured | Only Qwen2.5 72B Instruct measured |
| AI2 Reasoning Challenge | 94.5% | Not measured | Only Qwen2.5 72B Instruct measured |
| LMArena Text: science | 1275 | 1430 | Beam 1.0 501B A23B |
| LMArena Text: medicine and healthcare | 1258 | 1376 | Beam 1.0 501B A23B |
| LMArena Text: legal and government | 1288 | 1433 | Beam 1.0 501B A23B |
| LMArena Text: business and finance | 1253 | 1430 | Beam 1.0 501B A23B |
| Neither model has a result on the other 11 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Qwen2.5 72B Instruct | Beam 1.0 501B A23B | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1250 | Only Beam 1.0 501B A23B measured |
| Design Arena: game dev | Not measured | 1224 | Only Beam 1.0 501B A23B measured |
| Neither model has a result on the other 7 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index012
| Benchmark | Qwen2.5 72B Instruct | Beam 1.0 501B A23B | Leader |
|---|---|---|---|
| IFBench | 36.9% | Not measured | Only Qwen2.5 72B Instruct measured |
| DTBench | 62.9% | Not measured | Only Qwen2.5 72B Instruct measured |
| LMCA | 13.4% | Not measured | Only Qwen2.5 72B Instruct measured |
| HellaSwag | 84.8% | Not measured | Only Qwen2.5 72B Instruct measured |
| WinoGrande | 82.3% | Not measured | Only Qwen2.5 72B Instruct measured |
| PIQA | 82.6% | Not measured | Only Qwen2.5 72B Instruct measured |
| LMArena Text | 1269 | 1425 | Beam 1.0 501B A23B |
| LMArena Text: instruction following | 1254 | 1430 | Beam 1.0 501B A23B |
| LMArena Text: creative writing | 1221 | 1390 | Beam 1.0 501B A23B |
| LMArena Text: English | 1283 | 1436 | Beam 1.0 501B A23B |
| LMArena Text: non-English | 1252 | 1413 | Beam 1.0 501B A23B |
| LMArena Text: Chinese | 1273 | 1424 | Beam 1.0 501B A23B |
| LMArena Text: German | 1234 | Not measured | Only Qwen2.5 72B Instruct measured |
| LMArena Text: Japanese | 1180 | Not measured | Only Qwen2.5 72B Instruct measured |
| LMArena Text: Korean | 1188 | Not measured | Only Qwen2.5 72B Instruct measured |
| LMArena Text: French | 1280 | 1461 | Beam 1.0 501B A23B |
| LMArena Text: Spanish | 1255 | Not measured | Only Qwen2.5 72B Instruct measured |
| LMArena Text: Russian | 1264 | 1412 | Beam 1.0 501B A23B |
| LMArena Text: multi-turn | 1272 | 1414 | Beam 1.0 501B A23B |
| LMArena Text: longer queries | 1281 | 1429 | Beam 1.0 501B A23B |
| LMArena Text: writing and language | 1247 | 1400 | Beam 1.0 501B A23B |
| LMArena Text: entertainment and media | 1211 | 1399 | Beam 1.0 501B A23B |
| Neither model has a result on the other 24 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen2.5 72B Instruct | Beam 1.0 501B A23B | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Qwen2.5 72B Instruct costs less
Repository review
50K input + 3K output tokens
Qwen2.5 72B Instruct costs less
Agent loop
200K input + 10K output tokens
Qwen2.5 72B Instruct costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Qwen2.5 72B Instruct | Reflection Beam 1.0 501B A23B |
|---|---|---|
| Maker | Qwen | Reflection |
| Weights | Open weights | Open weights |
| Released | September 19, 2024 | October 16, 2026 |
| Context window | 33K | 1.05M |
| Input $/Mtok | $0.36 | $0.35 |
| Output $/Mtok | $0.40 | $1.10 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen2.5 72B Instruct better than Beam 1.0 501B A23B for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Qwen2.5 72B Instruct for output tokens 2.8x cheaper ($0.40 vs $1.10 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.
Which is cheaper, Qwen2.5 72B Instruct or Beam 1.0 501B A23B?
Qwen2.5 72B Instruct costs $0.36 per million input tokens and $0.40 per million output tokens; Beam 1.0 501B A23B costs $0.35 and $1.10. Cost per solved task is known for neither of them.
Which has the bigger context window, Qwen2.5 72B Instruct or Beam 1.0 501B A23B?
Beam 1.0 501B A23B, with 1.05M tokens against 33K.
How many benchmarks is the Qwen2.5 72B Instruct vs Beam 1.0 501B A23B comparison based on?
23 benchmarks have a result for both models as of October 22, 2026. Qwen2.5 72B Instruct's coding index rests on 0 independent benchmarks and Beam 1.0 501B A23B's on 1. Where only one model has a result, the page says so instead of naming a winner.