Qwen2.5 VL 72B Instruct vs Reka Flash 3
Reka Flash 3 costs 5.0x less per output token than Qwen2.5 VL 72B Instruct ($0.20 vs $1.00 per million). Updated October 23, 2026; no benchmark has tested both models yet.
- Coding
- No data
- Overall
- No data
- Output $/M
- $1.00
- Coding
- No data
- Overall
- No data
- Output $/M
- $0.20
Qwen2.5 VL 72B Instruct or Reka Flash 3: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Qwen2.5 VL 72B Instruct for a larger context window (128K against 66K tokens).
No benchmark has tested both yet. Qwen2.5 VL 72B Instruct has results on OSWorld, Kagi LLM Benchmark and GeoBench; Reka Flash 3 on LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run) and AA Intelligence Index. Compare them on price and context instead.
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 Reka Flash 3 has a AA Intelligence Index result, 6.4.
Directional only
Long documents
Listed context window
Qwen2.5 VL 72B Instruct
Qwen2.5 VL 72B Instruct takes 128K tokens against 66K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Reka Flash 3
Qwen2.5 VL 72B Instruct $0.0013, Reka Flash 3 $0.0002 per turn.
List prices
At a glance
- Coding index
- Qwen2.5 VL 72B Instruct not benchmarked, Reka Flash 3 not benchmarked.
- Widest category
- None yet: no category has been tested on both models.
- Widest single gap
- None yet: no benchmark has tested both models.
- Output price
- Qwen2.5 VL 72B Instruct $1.00 against Reka Flash 3 $0.20 per million output tokens, 5.0x apart.
- Context window
- Qwen2.5 VL 72B Instruct takes 128K tokens, Reka Flash 3 66K.
Benchmark by benchmark
Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.
CodingDirectional onlySix of these boards feed the Vibe Coding Index2 boards measured
| Benchmark | Qwen2.5 VL 72B Instruct | Reka Flash 3 | Leader |
|---|---|---|---|
| LiveCodeBench (Artificial Analysis run) | Not measured | 43.5% | Only Reka Flash 3 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 0.0% | Only Reka Flash 3 measured |
| Neither model has a result on the other 41 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Qwen2.5 VL 72B Instruct | Reka Flash 3 | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 6.4 | Only Reka Flash 3 measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards measured
| Benchmark | Qwen2.5 VL 72B Instruct | Reka Flash 3 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | Not measured | 0.0% | Only Reka Flash 3 measured |
| BALROG | Not measured | 29.2% | Only Reka Flash 3 measured |
| OSWorld | 5.0% | Not measured | Only Qwen2.5 VL 72B Instruct measured |
| Neither model has a result on the other 39 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index3 boards measured
| Benchmark | Qwen2.5 VL 72B Instruct | Reka Flash 3 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | Not measured | 52.9% | Only Reka Flash 3 measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 4.4% | Only Reka Flash 3 measured |
| Kagi LLM Benchmark | 36.0% | Not measured | Only Qwen2.5 VL 72B Instruct measured |
| Neither model has a result on the other 20 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | Qwen2.5 VL 72B Instruct | Reka Flash 3 | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 33.7 | Only Reka Flash 3 measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 33.7% | Only Reka Flash 3 measured |
| Neither model has a result on the other 12 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | Qwen2.5 VL 72B Instruct | Reka Flash 3 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | Not measured | 66.9% | Only Reka Flash 3 measured |
| GeoBench | 62.0% | Not measured | Only Qwen2.5 VL 72B Instruct measured |
| Neither model has a result on the other 18 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index5 boards measured
| Benchmark | Qwen2.5 VL 72B Instruct | Reka Flash 3 | Leader |
|---|---|---|---|
| IFBench | Not measured | 30.4% | Only Reka Flash 3 measured |
| Long context reasoning (AA-LCR) | Not measured | 0.0% | Only Reka Flash 3 measured |
| LMArena Vision | 1107 | Not measured | Only Qwen2.5 VL 72B Instruct measured |
| LMArena Vision: English | 1115 | Not measured | Only Qwen2.5 VL 72B Instruct measured |
| LMArena Vision: Chinese | 1107 | Not measured | Only Qwen2.5 VL 72B Instruct measured |
| Neither model has a result on the other 43 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
Reka Flash 3 costs less
Repository review
50K input + 3K output tokens
Reka Flash 3 costs less
Agent loop
200K input + 10K output tokens
Reka Flash 3 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 VL 72B Instruct | Reka Flash 3 |
|---|---|---|
| Maker | Qwen | Reka |
| Weights | Open weights | Open weights |
| Released | February 1, 2025 | March 12, 2025 |
| Context window | 128K | 66K |
| Input $/Mtok | $0.80 | $0.10 |
| Output $/Mtok | $1.00 | $0.20 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen2.5 VL 72B Instruct better than Reka Flash 3 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Qwen2.5 VL 72B Instruct for a larger context window (128K against 66K tokens).
Which is cheaper, Qwen2.5 VL 72B Instruct or Reka Flash 3?
Qwen2.5 VL 72B Instruct costs $0.80 per million input tokens and $1.00 per million output tokens; Reka Flash 3 costs $0.10 and $0.20. Cost per solved task is known for neither of them.
Which has the bigger context window, Qwen2.5 VL 72B Instruct or Reka Flash 3?
Qwen2.5 VL 72B Instruct, with 128K tokens against 66K.
Has any benchmark tested both Qwen2.5 VL 72B Instruct and Reka Flash 3?
No benchmark has tested both yet. Qwen2.5 VL 72B Instruct has results on OSWorld, Kagi LLM Benchmark and GeoBench; Reka Flash 3 on LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run) and AA Intelligence Index. Compare them on price and context instead. Data as of October 23, 2026.